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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τας
    -0.08
     schedules
    -0.08
     dialogs
    -0.08
     banners
    -0.07
    <|endoftext|>
    -0.07
     blends
    -0.07
    τε
    -0.07
     blankets
    -0.07
     tents
    -0.07
     vari
    -0.07
    POSITIVE LOGITS
     Aufgabe
    0.09
    女孩
    0.08
    ுமே
    0.08
     गण
    0.08
     ગણ
    0.08
     Psychic
    0.08
     Odds
    0.08
     вычис
    0.08
    .figure
    0.08
     convencional
    0.08
    Act Density 0.083%

    No Known Activations