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

    Neuronpedia

    INDEX
    Explanations

    the start of a code block or a programming structure

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

    Text snippets followed by punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    provide potentially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     al
    -0.54
     Hal
    -0.49
     Bra
    -0.47
    ISING
    -0.47
     Sa
    -0.46
     bra
    -0.46
     ma
    -0.46
     Gan
    -0.46
    ters
    -0.46
    ente
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    1.34
     Normdatei
    1.08
    webElement
    1.02
    хьтан
    0.98
     <=",
    0.95
     للمعارف
    0.93
     CreateTagHelper
    0.91
    出版年
    0.91
     JpaRepository
    0.90
    RectangleBorder
    0.89
    Act Density 0.651%

    No Known Activations