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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace characters or empty segments in the text

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

    code header declarations and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رشف
    -0.57
    UserScript
    -0.48
    })->
    -0.48
     @}
    -0.42
     SwitchCompat
    -0.40
    WithIOException
    -0.40
    /}.
    -0.39
     foils
    -0.38
    })`
    -0.38
    <?,
    -0.38
    POSITIVE LOGITS
    ⓘ
    0.47
     avoient
    0.46
     Audiodateien
    0.41
    /*
    0.41
    TagMode
    0.41
     nonatomic
    0.39
     prisonniers
    0.39
     chofe
    0.38
    adaptiveStyles
    0.38
     
    0.38
    Act Density 0.000%

    No Known Activations