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

    Neuronpedia

    INDEX
    Explanations

    position relative;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     memorize
    0.97
     preamble
    0.91
     renormal
    0.87
     preface
    0.86
     hypergeometric
    0.85
    ু
    0.84
     phrasing
    0.84
    ರುತ್ತದೆ
    0.83
    誹
    0.83
     moth
    0.82
    POSITIVE LOGITS
    ق
    1.03
     Jefe
    0.97
    zig
    0.95
    حسن
    0.94
    icked
    0.92
     Vorsitz
    0.92
     heureux
    0.91
    ح
    0.91
    Bounds
    0.89
    folios
    0.86
    Act Density 0.001%

    No Known Activations