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

    Neuronpedia

    INDEX
    Explanations

    valued

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .orange
    -0.07
     obstacle
    -0.06
     이전
    -0.06
     paint
    -0.06
     outside
    -0.06
     Leo
    -0.06
     Apostle
    -0.06
     liberties
    -0.06
    stří
    -0.06
    language
    -0.06
    POSITIVE LOGITS
     valued
    0.07
    _aff
    0.07
    .Def
    0.07
    .uni
    0.06
    :name
    0.06
    emu
    0.06
     expects
    0.06
    gard
    0.06
    _MUT
    0.06
    thed
    0.06
    Act Density 0.004%

    No Known Activations