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

    Neuronpedia

    INDEX
    Explanations

    programming-related function calls and definitions

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

    Code, constants, and technical terms

    np_acts-logits-general · gemini-2.0-flash

    technical identifiers and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TestBed
    -0.65
    TestBed
    -0.58
    nextProps
    -0.46
    ])))
    -0.45
    ngOn
    -0.43
     iprot
    -0.42
    ))))
    -0.42
     dis
    -0.42
     direct
    -0.41
     vast
    -0.40
    POSITIVE LOGITS
     ſtand
    0.80
     himſelf
    0.78
     ſen
    0.74
     poffible
    0.74
     ſeveral
    0.73
    ismet
    0.73
     Jefus
    0.73
     itſelf
    0.72
     myſelf
    0.72
     beſt
    0.72
    Act Density 0.301%

    No Known Activations