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

    Neuronpedia

    INDEX
    Explanations

    specific word followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     can
    0.50
     districts
    0.49
     terminus
    0.48
     Py
    0.46
     boundary
    0.46
     comparison
    0.45
     (
    0.44
     pick
    0.44
     contingency
    0.44
     cytology
    0.44
    POSITIVE LOGITS
     المحاضره
    0.58
    mensaje
    0.54
    Hlav
    0.54
    0.52
    tı
    0.52
    ຮູ້
    0.51
    lendir
    0.50
    umlahan
    0.50
    ចែកចាយ
    0.50
     مهمه
    0.49
    Act Density 0.000%

    No Known Activations