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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ustering
    -0.07
     กรกฎ
    -0.07
    }.${
    -0.06
     prepar
    -0.06
    ♠
    -0.06
     Sche
    -0.06
    _registers
    -0.06
     Chung
    -0.06
     Тому
    -0.06
    ::$
    -0.06
    POSITIVE LOGITS
     believed
    0.08
     estudio
    0.07
     believe
    0.07
    predicted
    0.06
     vui
    0.06
     believes
    0.06
    iiii
    0.06
     getLast
    0.06
     reward
    0.06
    ,pos
    0.06
    Act Density 0.008%

    No Known Activations