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

    Neuronpedia

    INDEX
    Explanations

    references to popularity and common usage of various subjects

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

    the word "popular"

    np_acts-logits-general · gemini-2.0-flash

    popular / popularity / popularly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perfectly
    -0.55
    perfectly
    -0.53
     prochains
    -0.51
    Perfectly
    -0.50
    inib
    -0.46
    ResumeLayout
    -0.46
     Perfectly
    -0.45
    enol
    -0.45
    ()]);
    -0.43
    BeginInit
    -0.43
    POSITIVE LOGITS
     populares
    0.99
     among
    0.95
     auprès
    0.94
     Theſe
    0.91
     populaire
    0.91
     amongst
    0.89
    popular
    0.88
     POPULAR
    0.88
     popular
    0.87
     myſelf
    0.86
    Act Density 0.203%

    No Known Activations