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

    Neuronpedia

    INDEX
    Explanations

    descriptions of the condition of objects or places

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

    condition or shape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sendok
    -0.41
     typelib
    -0.39
    뀜
    -0.39
     république
    -0.39
    principalColumn
    -0.38
     traseira
    -0.37
     involuntarily
    -0.35
     appartements
    -0.35
    phem
    -0.35
     lais
    -0.35
    POSITIVE LOGITS
     Condition
    0.90
     condition
    0.86
     CONDITION
    0.78
    Condition
    0.76
    condition
    0.73
    CONDITION
    0.72
     Kondisi
    0.66
     kondisi
    0.61
     deterioration
    0.61
     deterior
    0.60
    Act Density 0.150%

    No Known Activations