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

    Neuronpedia

    INDEX
    Explanations

    fi and fl ligatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ोंग
    0.64
    ेंच
    0.63
    ంట్
    0.61
     выяв
    0.61
     определения
    0.60
    ToReference
    0.60
    िग
    0.59
    ă
    0.59
    fect
    0.57
     ETF
    0.57
    POSITIVE LOGITS
    4
    0.79
    =
    0.73
    5
    0.70
    {
    0.67
    ,’
    0.66
    0.64
    .’
    0.63
    ’.
    0.62
     in
    0.61
    9
    0.61
    Act Density 0.001%

    No Known Activations