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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their context in programming or configuration settings

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

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.76
    mpagne
    -0.73
    AnimationsModule
    -0.70
    AnchorStyles
    -0.69
    看去
    -0.67
    Hentet
    -0.66
    ſicht
    -0.66
     ANGELES
    -0.65
    rungsseite
    -0.63
    tershire
    -0.63
    POSITIVE LOGITS
    But
    0.34
    I
    0.32
    。
    0.32
    PDT
    0.32
    Cuando
    0.31
    When
    0.30
    Når
    0.30
    ，
    0.29
    ByUser
    0.29
    TP
    0.29
    Act Density 1.026%

    No Known Activations