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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     particularmente
    -0.09
     Bengal
    -0.09
     particulièrement
    -0.09
     saib
    -0.09
     especialmente
    -0.08
     savvy
    -0.08
     estimating
    -0.08
    Tas
    -0.08
     særlig
    -0.08
    acal
    -0.08
    POSITIVE LOGITS
     קצר
    0.09
     succinct
    0.09
     корот
    0.08
     breve
    0.08
     мне
    0.08
     کوت
    0.08
     shortcut
    0.08
     shortened
    0.08
     resumen
    0.08
     kurz
    0.08
    Act Density 0.000%

    No Known Activations