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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax, specifically dealing with functions and data structure manipulation

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

    Code, file names, and/or variable names

    np_acts-logits-general · gemini-2.0-flash

    PL, script, print, Field, file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‹
    -0.48
     schwe
    -0.48
     :
    -0.47
    鈥
    -0.46
    ensch
    -0.45
     grand
    -0.45
    （※
    -0.45
     •
    -0.43
     still
    -0.43
    —
    -0.43
    POSITIVE LOGITS
    CloseOperation
    0.99
     betweenstory
    0.95
     tartalomajánló
    0.90
    OGND
    0.84
     Мексичка
    0.83
     unknownFields
    0.83
    ########.
    0.82
    abestanden
    0.82
    tvguidetime
    0.82
     oprot
    0.78
    Act Density 0.500%

    No Known Activations