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

    Neuronpedia

    INDEX
    Explanations

    symbols, mathematical operators, and contextual markers in written formulas or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    chosen during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.94
    ngdoc
    -0.73
     }}$}
    -0.70
     MessageBoxIcon
    -0.67
    AccessorTable
    -0.64
    ++
    -0.64
    .":
    -0.63
    ']):
    -0.63
    RegistryLite
    -0.63
     NSCoder
    -0.63
    POSITIVE LOGITS
    ↵↵
    0.43
     ordinaires
    0.32
    ↵
    0.31
     emperador
    0.31
     alimentaria
    0.30
    chappen
    0.30
     alimentaire
    0.30
     circulación
    0.29
    SUPPORTED
    0.28
     asistencia
    0.28
    Act Density 0.015%

    No Known Activations