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

    Neuronpedia

    INDEX
    Explanations

    complement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cos
    -0.07
    resi
    -0.07
    62
    -0.07
    암
    -0.06
     للأ
    -0.06
     rx
    -0.06
     Harding
    -0.06
    687
    -0.06
     elections
    -0.06
    ovid
    -0.06
    POSITIVE LOGITS
     модель
    0.07
     ment
    0.07
     Call
    0.07
     reciprocal
    0.07
     šest
    0.06
     versa
    0.06
    _DISCONNECT
    0.06
    .setdefault
    0.06
    [type
    0.06
    ект
    0.06
    Act Density 0.001%

    No Known Activations