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

    Neuronpedia

    INDEX
    Explanations

    creative works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divisor
    -0.08
     Tro
    -0.06
    JWT
    -0.06
    _SUR
    -0.06
    uild
    -0.06
     entrepreneurship
    -0.06
    тро
    -0.06
    composed
    -0.06
     предвар
    -0.06
    .ver
    -0.06
    POSITIVE LOGITS
    анной
    0.07
    _limits
    0.06
    (@(
    0.06
     Bau
    0.06
    (unittest
    0.06
    001
    0.06
     GDK
    0.06
     Yates
    0.06
    _temp
    0.06
    )','
    0.06
    Act Density 0.058%

    No Known Activations