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

    Neuronpedia

    INDEX
    Explanations

    formula variable definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    સ્ક
    0.46
     لیکن
    0.44
    larla
    0.44
    ->$
    0.43
     videolar
    0.42
     फ्रॉम
    0.41
     જોઈએ
    0.40
    ்ட
    0.40
    rated
    0.40
     تیار
    0.40
    POSITIVE LOGITS
    (
    0.51
    être
    0.48
    ;
    0.48
     demur
    0.47
    ，
    0.46
    /
    0.46
    :
    0.46
    ෙහි
    0.46
    ،
    0.46
     में
    0.45
    Act Density 0.001%

    No Known Activations