Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements related to accidental or unintentional incidents, especially those causing harm or requiring emergency response

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before/after location-related terms

    np_acts-logits-general · gemini-2.0-flash

    officials reporting incidents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="@+
    -0.58
    Months
    -0.54
    ReusableCell
    -0.51
    imageshack
    -0.48
    offsetof
    -0.47
    diğinde
    -0.47
     Accepted
    -0.47
     months
    -0.46
     recognised
    -0.45
     Baillargeon
    -0.45
    POSITIVE LOGITS
     cordon
    0.73
    estrian
    0.59
     = 
    0.58
     evacuate
    0.58
    ährend
    0.58
    oplan
    0.57
     temporarily
    0.57
     traffic
    0.56
     withRouter
    0.56
    ientôt
    0.56
    Act Density 0.101%

    No Known Activations