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

    Neuronpedia

    INDEX
    Explanations

    specific names and proper nouns related to individuals, places, and brands

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

    Abbreviations

    np_acts-logits-general · gemini-2.0-flash

    Aussie spec fic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.94
     reaſon
    -0.84
     myſelf
    -0.84
     themſelves
    -0.83
     quæ
    -0.82
     becauſe
    -0.81
     يتيمه
    -0.80
     raiſ
    -0.80
     againſt
    -0.76
     uſed
    -0.76
    POSITIVE LOGITS
    gie
    0.77
    bie
    0.74
    zzie
    0.69
    mie
    0.69
    sie
    0.67
    gs
    0.67
     Aussie
    0.67
    ie
    0.66
    ggie
    0.66
    ggies
    0.65
    Act Density 0.309%

    No Known Activations