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

    Neuronpedia

    INDEX
    Explanations

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     présents
    -0.08
     December
    -0.07
    istische
    -0.07
     saha
    -0.07
     présentes
    -0.07
    lub
    -0.07
     presenti
    -0.07
     presence
    -0.07
    viz
    -0.07
    mandu
    -0.07
    POSITIVE LOGITS
     чуж
    0.09
     olyan
    0.09
     એવા
    0.09
     invál
    0.09
     нест
    0.08
     genuinely
    0.08
    _INVALID
    0.08
     unsuitable
    0.08
    荒
    0.08
     unforgettable
    0.08
    Act Density 0.127%

    No Known Activations