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

    Neuronpedia

    INDEX
    Explanations

    competition or tournament

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ategory
    0.63
    ancel
    0.61
    ILL
    0.59
    cted
    0.57
    ngModel
    0.57
    venuti
    0.56
    ressed
    0.55
    ally
    0.55
    agon
    0.54
    ikt
    0.54
    POSITIVE LOGITS
     aden
    0.68
     the
    0.65
     presentes
    0.63
     are
    0.63
    ﻫ
    0.62
    ت
    0.62
    ເອ
    0.61
     Réponses
    0.59
    ప్ర
    0.58
     Созда
    0.58
    Act Density 0.000%

    No Known Activations