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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “To
    -0.07
    Replace
    -0.07
     WK
    -0.06
    .collect
    -0.06
    .extensions
    -0.06
    /entity
    -0.06
    .assert
    -0.06
     barcode
    -0.06
    RuleContext
    -0.06
     modify
    -0.06
    POSITIVE LOGITS
     отношения
    0.07
    ALLY
    0.06
    VAS
    0.06
    NEL
    0.06
     IBM
    0.06
    -touch
    0.06
    Channels
    0.06
    ett
    0.06
     direkt
    0.06
    IÓN
    0.06
    Act Density 0.029%

    No Known Activations