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

    Neuronpedia

    INDEX
    Explanations

    estimations and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inch
    -0.06
     gran
    -0.06
    taj
    -0.06
     squirrel
    -0.06
    ागर
    -0.06
    ThanOr
    -0.06
     hran
    -0.06
     eylem
    -0.06
     توضی
    -0.06
     гара
    -0.06
    POSITIVE LOGITS
     matches
    0.07
     Fitness
    0.06
    *b
    0.06
    [source
    0.06
    .phi
    0.06
    KEY
    0.06
     Jong
    0.06
     THEME
    0.06
    $query
    0.06
    -complete
    0.06
    Act Density 0.029%

    No Known Activations