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

    Neuronpedia

    INDEX
    Explanations

    non-terminal punctuation and formatting symbols in text

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

    panty shots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.39
     tornillos
    -0.31
    expandindo
    -0.28
     accidentes
    -0.28
     linkovi
    -0.28
    rizona
    -0.28
     Copyright
    -0.27
    ftagPool
    -0.27
     bileklik
    -0.27
    ENCODING
    -0.26
    POSITIVE LOGITS
    PerformLayout
    0.65
     パンチラ
    0.60
    <unused52>
    0.59
    <unused68>
    0.58
    <unused41>
    0.58
    <unused23>
    0.58
    <unused17>
    0.58
    <unused14>
    0.58
    <unused3>
    0.58
    [@BOS@]
    0.58
    Act Density 0.851%

    No Known Activations