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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    49
    -0.08
    136
    -0.08
    -bottom
    -0.07
     buzz
    -0.07
    erdem
    -0.07
     sash
    -0.07
    无法
    -0.07
     inspiración
    -0.07
    _TMP
    -0.07
    TOP
    -0.07
    POSITIVE LOGITS
     domen
    0.08
    folder
    0.08
    жение
    0.08
    டுத்து
    0.07
     Weinstein
    0.07
    ಡು
    0.07
     Assim
    0.07
    стер
    0.07
    iddwa
    0.07
     worksheets
    0.07
    Act Density 0.078%

    No Known Activations