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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    resi
    -0.07
     methodName
    -0.06
    喔
    -0.06
     hol
    -0.06
     giving
    -0.06
     almış
    -0.06
    iscing
    -0.06
     Scal
    -0.06
    greso
    -0.06
     oppressed
    -0.06
    POSITIVE LOGITS
    PATCH
    0.06
     `/
    0.06
    ี่
    0.06
    _attack
    0.06
    //
    0.06
    Reason
    0.06
    _people
    0.06
    GB
    0.06
    Encode
    0.06
    уска
    0.06
    Act Density 0.000%

    No Known Activations