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

    Neuronpedia

    INDEX
    Explanations

    threat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mệ
    -0.07
     nach
    -0.06
    avir
    -0.06
     Diamonds
    -0.06
    (Label
    -0.06
    ้ใน
    -0.06
    breaker
    -0.06
     Эти
    -0.06
    uevo
    -0.06
     digits
    -0.06
    POSITIVE LOGITS
    .awt
    0.07
    .sql
    0.06
     selenium
    0.06
    .pipe
    0.06
    ALLERY
    0.06
    0.06
     Hard
    0.06
    :pointer
    0.06
     Winchester
    0.06
     closure
    0.06
    Act Density 0.000%

    No Known Activations