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

    Neuronpedia

    INDEX
    Explanations

    words followed by "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鳎
    0.38
    스러운
    0.37
     童
    0.35
    ratingBarStyle
    0.34
    神経
    0.34
     വേണ്ടി
    0.34
     পক্ষে
    0.33
    ളെ
    0.33
    lefthar
    0.33
    0.33
    POSITIVE LOGITS
    To
    1.88
    to
    1.86
     To
    1.73
     to
    1.44
     TO
    1.20
     तो
    1.12
     то
    1.12
    TO
    1.12
    ToServer
    0.97
    ToAction
    0.96
    Act Density 0.084%

    No Known Activations