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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sabha
    -0.07
    .Equal
    -0.06
    .Scale
    -0.06
     Tears
    -0.06
    930
    -0.06
    ходит
    -0.06
    727
    -0.06
    /<?
    -0.06
    .Filter
    -0.06
     disproportionate
    -0.06
    POSITIVE LOGITS
     eta
    0.07
     samp
    0.07
     stellar
    0.06
    ्ध
    0.06
     reinforcing
    0.06
    eguard
    0.06
     fused
    0.06
    cedures
    0.06
     metallic
    0.06
    еріг
    0.06
    Act Density 0.003%

    No Known Activations