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

    Neuronpedia

    INDEX
    Explanations

    stopping and starting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ~
    -0.07
     filesize
    -0.06
     (&
    -0.06
     bullets
    -0.06
     convenience
    -0.06
     aggressively
    -0.06
     sí
    -0.06
    [g
    -0.06
    _plain
    -0.06
    Mark
    -0.06
    POSITIVE LOGITS
     možné
    0.06
    ス
    0.06
    onas
    0.06
    aniu
    0.06
    oldem
    0.06
     اهل
    0.06
    _supp
    0.06
     DISP
    0.05
     Dop
    0.05
     laughter
    0.05
    Act Density 0.084%

    No Known Activations