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

    Neuronpedia

    INDEX
    Explanations

    har

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ması
    -0.06
    َو
    -0.06
    .getModel
    -0.06
    启
    -0.06
     originals
    -0.06
     theorem
    -0.05
    一页
    -0.05
     attendee
    -0.05
    열
    -0.05
     Gel
    -0.05
    POSITIVE LOGITS
    .solution
    0.07
    rocket
    0.07
    _COUNTER
    0.06
    (public
    0.06
     Sunset
    0.06
    FullScreen
    0.06
    CKET
    0.06
    _SF
    0.06
     ATH
    0.06
    _VOICE
    0.06
    Act Density 0.002%

    No Known Activations