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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    linewidth
    -0.07
    _related
    -0.07
    ;?></
    -0.07
    kání
    -0.06
    .Reg
    -0.06
    (feature
    -0.06
     trio
    -0.06
     *}↵↵
    -0.06
    _Global
    -0.06
    .tags
    -0.06
    POSITIVE LOGITS
    rst
    0.06
     CALL
    0.06
     DEAL
    0.06
    ("//
    0.06
    TH
    0.06
    ModelProperty
    0.06
    olynomial
    0.06
     observational
    0.06
     sayı
    0.06
    有什么
    0.06
    Act Density 0.002%

    No Known Activations