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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and notations related to programming or mathematical concepts

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

    Code, math, or uncommon punctuation

    np_acts-logits-general · gemini-2.0-flash

    section or list start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.97
    tagHelperRunner
    -0.95
    Personendaten
    -0.88
    SequentialGroup
    -0.80
     Saltar
    -0.78
     transfieras
    -0.78
    __(/*!
    -0.76
    تقاوى
    -0.74
     typelib
    -0.72
    ArgsConstructor
    -0.72
    POSITIVE LOGITS
    </em>
    0.73
     informée
    0.64
    rrggbb
    0.55
    例句
    0.52
     estimés
    0.52
     tartalomajánló
    0.49
     ^(
    0.48
    jerg
    0.48
    estacks
    0.47
    ↵↵
    0.47
    Act Density 3.388%

    No Known Activations