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

    Neuronpedia

    INDEX
    Explanations

    Apache software, foundations, licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ﺍﻟ
    0.98
     църква
    0.93
     hermosa
    0.91
     Tokugawa
    0.91
     ojos
    0.90
     extranj
    0.90
     Ս
    0.89
     haies
    0.89
     griega
    0.89
     İyi
    0.86
    POSITIVE LOGITS
    apache
    1.15
    ة
    1.00
    2
    0.95
    Apache
    0.91
    ה
    0.91
    （
    0.87
    (
    0.84
    ли
    0.84
    ：
    0.82
    ă
    0.79
    Act Density 0.003%

    No Known Activations