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

    Neuronpedia

    INDEX
    Explanations

    filler words and phrases in speech

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

    Follows punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    Palmer gave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dilution
    -0.46
    Retirement
    -0.42
    ########.
    -0.42
    unrecognized
    -0.41
    Wut
    -0.40
    normalized
    -0.39
     indestructible
    -0.39
    Local
    -0.39
    alahan
    -0.38
     Locally
    -0.38
    POSITIVE LOGITS
     nahilalakip
    0.83
     initComponents
    0.81
    expandindo
    0.81
    Referencie
    0.78
    aarrggbb
    0.78
     للمعارف
    0.77
    setViewportView
    0.77
    AlterField
    0.76
     كومونز
    0.76
     nakalista
    0.75
    Act Density 0.291%

    No Known Activations