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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

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

    Followed by GUI-related terms

    np_acts-logits-general · gemini-2.0-flash

    in multiple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.62
     as
    -0.57
    :
    -0.55
     e
    -0.55
     ve
    -0.53
    ;
    -0.52
     here
    -0.52
     del
    -0.52
     na
    -0.51
     sal
    -0.51
    POSITIVE LOGITS
     الرياضيه
    1.00
     myſelf
    0.99
    httphttps
    0.95
     itſelf
    0.94
     }}$}
    0.92
    uxxxx
    0.91
    Autoritní
    0.86
    Location
    0.85
     houſe
    0.84
    ſelf
    0.83
    Act Density 0.010%

    No Known Activations