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

    Neuronpedia

    INDEX
    Explanations

    expressions of measurement or evaluation in the context of achievements or performance

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

    Punctuation marks, especially quotes

    np_acts-logits-general · gemini-2.0-flash

    opening quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.85
    errHandler
    -0.84
    MLLoader
    -0.83
     nahilalakip
    -0.83
    SuspendLayout
    -0.82
    €¦
    -0.81
     Majefty
    -0.80
     Efq
    -0.79
     $_"
    -0.78
    KURZBESCHREIBUNG
    -0.77
    POSITIVE LOGITS
     “
    2.96
     "
    2.74
    “
    2.33
    「
    1.98
     „
    1.93
     “[
    1.92
     «
    1.81
     “…
    1.75
    ，“
    1.75
     “(
    1.72
    Act Density 0.550%

    No Known Activations