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

    Neuronpedia

    INDEX
    Explanations

    toxicity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     size
    -0.07
    Moh
    -0.07
    proc
    -0.07
    uire
    -0.07
     Stat
    -0.06
    駐
    -0.06
    .K
    -0.06
    核准
    -0.06
     mu
    -0.06
    icon
    -0.06
    POSITIVE LOGITS
    -has
    0.08
     onCancel
    0.08
     Fin
    0.08
    啭
    0.07
    -offs
    0.07
    :');↵
    0.07
    썜
    0.07
    /el
    0.07
    )?.
    0.07
     frais
    0.07
    Act Density 0.083%

    No Known Activations