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

    Neuronpedia

    INDEX
    Explanations

    date and time formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    доволь
    0.63
    步行
    0.62
    ˌ
    0.60
    آخر
    0.59
    uteur
    0.55
    šo
    0.55
     أشهر
    0.55
     Kabupaten
    0.55
    лық
    0.55
    щего
    0.55
    POSITIVE LOGITS
     IIT
    0.63
     coatings
    0.62
     IPython
    0.62
    rzeb
    0.61
     StyleSheet
    0.61
     Coatings
    0.58
    Ⅱ
    0.58
     capital
    0.58
     UCLA
    0.57
    Expr
    0.57
    Act Density 0.116%

    No Known Activations