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

    Neuronpedia

    INDEX
    Explanations

    web development and scripting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    1.37
    .
    1.20
    3
    1.20
    ه
    1.13
    وم
    1.09
    а
    1.09
    る
    1.08
    т
    1.07
    и
    1.06
    ா
    1.02
    POSITIVE LOGITS
     in
    1.06
     szervez
    0.90
    ने
    0.89
     autore
    0.89
     web
    0.86
     igen
    0.84
    翮
    0.82
     o
    0.82
    LE
    0.79
     yab
    0.77
    Act Density 0.021%

    No Known Activations