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

    Neuronpedia

    INDEX
    Explanations

    numerical lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legalization
    0.69
    missible
    0.65
    Listener
    0.64
    ீர
    0.64
    rimin
    0.63
    VID
    0.63
    sciutto
    0.63
    jis
    0.62
    WindowTitle
    0.61
    DST
    0.61
    POSITIVE LOGITS
     arqu
    0.73
     arred
    0.69
     તમામ
    0.69
     todos
    0.69
     poc
    0.66
     Rating
    0.66
    Rating
    0.65
     заре
    0.64
     करनाल
    0.64
     Neto
    0.63
    Act Density 0.110%

    No Known Activations