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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sent
    -0.07
     вет
    -0.07
    Vac
    -0.06
     значение
    -0.06
     чай
    -0.06
    Advance
    -0.06
     Müz
    -0.06
     пн
    -0.06
    holds
    -0.06
     stale
    -0.06
    POSITIVE LOGITS
     curves
    0.07
    fps
    0.06
     Infos
    0.06
    IFICATIONS
    0.06
    ност
    0.06
     horribly
    0.06
    (rotation
    0.06
     measurements
    0.06
     ASAP
    0.06
    culator
    0.06
    Act Density 0.073%

    No Known Activations