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

    Neuronpedia

    INDEX
    Explanations

    technology posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :The
    -0.07
    etect
    -0.06
    ^.
    -0.06
    $error
    -0.06
    urations
    -0.06
    CY
    -0.06
     diamond
    -0.06
     probation
    -0.06
    thest
    -0.06
    allows
    -0.06
    POSITIVE LOGITS
     vybav
    0.07
    _arc
    0.07
     عز
    0.07
    овід
    0.06
    567
    0.06
    宇
    0.06
     напрям
    0.06
    (Uri
    0.06
    (tf
    0.06
     ander
    0.06
    Act Density 0.196%

    No Known Activations