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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and functions involving fractions, variables, and constants

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

    Mathematical expressions or symbols

    np_acts-logits-general · gemini-2.0-flash

    fractions and pi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.82
     EconPapers
    -0.63
    ThroughAttribute
    -0.59
    Controllo
    -0.59
    ština
    -0.58
    UnusedPrivate
    -0.57
    webElement
    -0.57
     nakalista
    -0.56
     autorytatywna
    -0.55
    ScopeManager
    -0.53
    POSITIVE LOGITS
     numerator
    0.66
    }{
    0.59
    ện
    0.55
     than
    0.54
    дото
    0.54
    getReference
    0.50
    ̣n
    0.50
    djangoproject
    0.49
    стреча
    0.49
     obiettivo
    0.49
    Act Density 0.708%

    No Known Activations