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

    Neuronpedia

    INDEX
    Explanations

    elemental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ће
    -0.09
     paro
    -0.08
    Charles
    -0.08
     reš
    -0.08
     fraude
    -0.08
    Ensure
    -0.07
    Dern
    -0.07
    Utf
    -0.07
     loaf
    -0.07
    ительная
    -0.07
    POSITIVE LOGITS
     стих
    0.09
     naturale
    0.09
     liquide
    0.09
     swirling
    0.09
     fountains
    0.08
     minerals
    0.08
     природ
    0.08
     Minerals
    0.08
     substances
    0.08
    力量
    0.08
    Act Density 0.004%

    No Known Activations