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

    Neuronpedia

    INDEX
    Explanations

    code/config files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    our
    -0.07
     gro
    -0.07
    $i
    -0.07
     Tout
    -0.06
    ़ो
    -0.06
    又
    -0.06
    ↵  ↵
    -0.06
    _contains
    -0.06
     numeric
    -0.06
    Fonts
    -0.06
    POSITIVE LOGITS
    (IService
    0.07
    láda
    0.07
     MIPS
    0.07
    oriously
    0.06
     bilin
    0.06
    izophren
    0.06
    ','
    0.06
    IMPLIED
    0.06
    ABI
    0.06
    .article
    0.06
    Act Density 0.073%

    No Known Activations