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

    Neuronpedia

    INDEX
    Explanations

    references to wine and its production process

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

    Quantities, percentages, or ratios

    np_acts-logits-general · gemini-2.0-flash

    color adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.72
    ConstraintMaker
    -0.72
    تقاوى
    -0.69
    MigrationBuilder
    -0.69
    PerformLayout
    -0.65
    cookieParser
    -0.64
    __':
    -0.64
    InvalidProtocol
    -0.64
     zvuky
    -0.62
     scom
    -0.61
    POSITIVE LOGITS
     hybrid
    0.61
     dark
    0.61
     blend
    0.59
     light
    0.59
    hybrid
    0.59
     Hybrid
    0.58
     blended
    0.55
     pale
    0.55
    Hybrid
    0.54
     blonde
    0.53
    Act Density 0.084%

    No Known Activations