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

    Neuronpedia

    INDEX
    Explanations

    regulatory compliance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CRYPTO
    -0.07
    (Integer
    -0.07
    Insensitive
    -0.07
    \Component
    -0.07
    "github
    -0.06
     Bronze
    -0.06
    (priority
    -0.06
    (xs
    -0.06
    _eng
    -0.06
     Contains
    -0.06
    POSITIVE LOGITS
    吹
    0.06
     fb
    0.06
    Seleccion
    0.06
    .transpose
    0.06
     courtroom
    0.06
     rut
    0.06
     ecc
    0.06
    以
    0.06
     bait
    0.06
     eup
    0.06
    Act Density 0.011%

    No Known Activations