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

    Neuronpedia

    INDEX
    Explanations

    references to threats

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

    threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pab
    -0.50
     Kingston
    -0.49
     Pab
    -0.48
    ậu
    -0.44
     Nana
    -0.43
     *)
    -0.43
     cob
    -0.43
    bgColor
    -0.41
     pab
    -0.41
     Alva
    -0.41
    POSITIVE LOGITS
     threat
    2.14
    threat
    1.95
     Threat
    1.94
    Threat
    1.91
     threats
    1.77
    Threats
    1.61
     Threats
    1.61
     amenaza
    1.53
     threaten
    1.50
     threatening
    1.43
    Act Density 0.005%

    No Known Activations