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

    Neuronpedia

    INDEX
    Explanations

    symbols and structural elements in written code or mathematical expressions

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

    mathematical problem explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.56
    EDEFAULT
    -0.54
    UnusedPrivate
    -0.52
    delwed
    -0.50
     فريبيس
    -0.48
    InjectAttribute
    -0.47
     autorytatywna
    -0.46
    MigrationBuilder
    -0.43
    GEBURTSDATUM
    -0.42
     dormitórios
    -0.42
    POSITIVE LOGITS
     explanations
    0.63
     explanation
    0.60
     answers
    0.56
     steps
    0.47
     calculations
    0.46
     procedimiento
    0.46
     réponses
    0.45
    解答
    0.45
     student
    0.45
     answer
    0.45
    Act Density 0.061%

    No Known Activations