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

    Neuronpedia

    INDEX
    Explanations

    summary judgment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consid
    -0.08
     młod
    -0.07
     являются
    -0.07
     hind
    -0.07
     pollut
    -0.07
     béné
    -0.07
     Creature
    -0.07
     אתם
    -0.06
    _fw
    -0.06
     Brewing
    -0.06
    POSITIVE LOGITS
     crear
    0.07
    uze
    0.07
     troublesome
    0.06
    boBox
    0.06
    铎
    0.06
    让
    0.06
    读
    0.06
    UIS
    0.06
     senses
    0.06
    azel
    0.06
    Act Density 0.008%

    No Known Activations