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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ages
    -0.07
    -buffer
    -0.06
    алізації
    -0.06
     ماند
    -0.06
    FS
    -0.06
    Sanders
    -0.06
    刻
    -0.06
    (version
    -0.06
    ehr
    -0.06
    --){↵
    -0.06
    POSITIVE LOGITS
     Eug
    0.07
     食
    0.07
    _GUI
    0.06
     CCC
    0.06
     capitalize
    0.06
    assertCount
    0.06
    .EntityFrameworkCore
    0.06
     slashing
    0.06
     neh
    0.06
    .php
    0.06
    Act Density 0.004%

    No Known Activations