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

    Neuronpedia

    INDEX
    Explanations

    regular expressions, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tits
    -0.07
    ιβ
    -0.07
    βά
    -0.07
     ι
    -0.06
     attitude
    -0.06
    Latitude
    -0.06
     mev
    -0.06
    STDOUT
    -0.06
     tvoř
    -0.06
    罗
    -0.06
    POSITIVE LOGITS
    Selectable
    0.07
     grounding
    0.07
    JSImport
    0.07
    requete
    0.07
    _an
    0.06
    /detail
    0.06
    ',{
    0.06
     Authorization
    0.06
    scalar
    0.06
    .E
    0.06
    Act Density 0.003%

    No Known Activations