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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    をする
    -0.07
    _PL
    -0.06
    (Auth
    -0.06
    .invoice
    -0.06
    _I
    -0.06
     {{{
    -0.06
     unos
    -0.06
     kW
    -0.06
    —I
    -0.06
    ubes
    -0.06
    POSITIVE LOGITS
     získ
    0.07
     storyboard
    0.07
    christ
    0.06
    multi
    0.06
     originating
    0.06
     Patriot
    0.06
     digs
    0.06
     cine
    0.06
    frontend
    0.06
    phere
    0.06
    Act Density 0.041%

    No Known Activations