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

    Neuronpedia

    INDEX
    Explanations

    numeric values with a specific format or significance

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

    numbered section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.63
    ReusableCell
    -0.61
     ſei
    -0.56
    󠁮
    -0.55
     ModelExpression
    -0.55
     surla
    -0.54
     Infórmanos
    -0.53
     purpoſe
    -0.53
     שוליים
    -0.53
    saraba
    -0.53
    POSITIVE LOGITS
    subsubsection
    0.97
    INCREF
    0.47
    windowFixed
    0.43
    iri
    0.42
    deepEqual
    0.41
    vi
    0.40
    tig
    0.40
     necessitates
    0.39
    inii
    0.39
     true
    0.38
    Act Density 0.018%

    No Known Activations