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

    Neuronpedia

    INDEX
    Explanations

    intensity modifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .schema
    -0.06
     slashed
    -0.06
    であ
    -0.06
    셜
    -0.06
     무엇
    -0.06
     JsonRequest
    -0.06
    (skip
    -0.06
    =lambda
    -0.06
     slashing
    -0.06
    OI
    -0.05
    POSITIVE LOGITS
     тур
    0.07
     바라
    0.07
    _labels
    0.07
     quatre
    0.07
    _embed
    0.06
     магаз
    0.06
    .Completed
    0.06
     ücret
    0.06
     etmek
    0.06
     đẩy
    0.06
    Act Density 0.030%

    No Known Activations