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

    Neuronpedia

    INDEX
    Explanations

    font settings and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্লাই
    1.10
    лда
    1.04
    л
    1.02
     nyata
    1.00
     ба
    0.95
    י
    0.95
    volving
    0.92
    SEY
    0.92
    ر
    0.91
    াজার
    0.91
    POSITIVE LOGITS
    astic
    1.46
    awesome
    1.43
    unately
    1.31
    Awesome
    1.23
    inued
    1.23
     merah
    1.22
    HERSHEY
    1.19
     size
    1.15
    ogenetic
    1.15
     règ
    1.13
    Act Density 0.010%

    No Known Activations