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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assurance
    -0.07
    _features
    -0.06
    Dia
    -0.06
    inal
    -0.06
    wap
    -0.06
    Generator
    -0.06
    <G
    -0.06
     logs
    -0.06
    ("${
    -0.06
    .meta
    -0.06
    POSITIVE LOGITS
    organisms
    0.06
     еди
    0.06
     плат
    0.06
    realloc
    0.06
     Colbert
    0.06
    SEP
    0.06
    Рµ
    0.06
    ậc
    0.06
     cdecl
    0.06
     relentlessly
    0.06
    Act Density 0.014%

    No Known Activations