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

    Neuronpedia

    INDEX
    Explanations

    Filling in forms/spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unsafe
    -0.08
    אושר
    -0.07
    .epoch
    -0.07
     abdominal
    -0.07
     convertible
    -0.07
    🧸
    -0.07
    ,next
    -0.07
    Nonce
    -0.07
    mpz
    -0.07
    (dAtA
    -0.06
    POSITIVE LOGITS
    𝙡
    0.07
    m
    0.07
     первого
    0.07
    ético
    0.07
    ზ
    0.07
    Act
    0.07
    lı
    0.06
    tm
    0.06
    rt
    0.06
    pectives
    0.06
    Act Density 0.059%

    No Known Activations