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

    Neuronpedia

    INDEX
    Explanations

    numbers and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AMENTE
    1.02
    ETT
    0.87
    કોટ
    0.84
     または
    0.80
    വു
    0.77
    ETON
    0.75
    िकुलर
    0.75
     Chub
    0.75
    enment
    0.75
     Evet
    0.75
    POSITIVE LOGITS
    s
    1.04
    তে
    0.96
    ের
    0.91
    эд
    0.91
     время
    0.91
    тным
    0.89
    з
    0.89
     несколько
    0.85
    le
    0.84
    тную
    0.80
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.