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

    Neuronpedia

    INDEX
    Explanations

    code punctuation and keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IDE
    -0.07
     Cavaliers
    -0.07
     Straight
    -0.07
    .readInt
    -0.06
     nb
    -0.06
    Sorry
    -0.06
    иной
    -0.06
    ibile
    -0.06
    currentTime
    -0.06
    regions
    -0.06
    POSITIVE LOGITS
    _clk
    0.07
    洲
    0.07
    章
    0.06
     кл
    0.06
    럽
    0.06
    Juan
    0.06
    ;↵↵↵↵
    0.06
    ugg
    0.06
    anteed
    0.06
     payable
    0.06
    Act Density 0.059%

    No Known Activations