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

    Neuronpedia

    INDEX
    Explanations

    identifiers and variables in programming contexts

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

    inside or function scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.63
    SBATCH
    -0.61
     $_"
    -0.57
     समीक्षाओं
    -0.57
    GraphicsUnit
    -0.56
     newState
    -0.56
     queſta
    -0.56
    +#+
    -0.55
    jooq
    -0.54
     WALTZ
    -0.53
    POSITIVE LOGITS
     inside
    0.83
    Inside
    0.68
     Inside
    0.65
     dentro
    0.64
    inside
    0.63
     INSIDE
    0.61
    Билгалдахарш
    0.53
     outside
    0.52
     внутри
    0.52
     adentro
    0.49
    Act Density 0.339%

    No Known Activations