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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADF
    -0.07
     WORK
    -0.06
    oš
    -0.06
    칙
    -0.06
    络
    -0.06
     SOS
    -0.06
     případně
    -0.06
     worrying
    -0.06
    画像
    -0.06
    .FileWriter
    -0.06
    POSITIVE LOGITS
    Detroit
    0.07
     Detroit
    0.07
     Bitcoin
    0.06
    <bool
    0.06
    requent
    0.06
     hoş
    0.06
     fen
    0.06
    LED
    0.06
     Ard
    0.06
    Joe
    0.06
    Act Density 0.000%

    No Known Activations