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

    Neuronpedia

    INDEX
    Explanations

    certainly, Form, wing, Take

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    િ
    1.11
    ج
    0.88
    .
    0.87
     Rou
    0.79
    COME
    0.79
    ﻣ
    0.77
    ش
    0.77
    Pe
    0.74
     Pawan
    0.73
    7
    0.73
    POSITIVE LOGITS
     spezi
    1.04
    gray
    1.02
     gray
    0.88
    aar
    0.88
    জগ
    0.87
     möglicherweise
    0.86
     ആയി
    0.84
    arq
    0.84
     quería
    0.83
    ാരണ
    0.83
    Act Density 0.000%

    No Known Activations