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

    Neuronpedia

    INDEX
    Explanations

    specific structures in written text, particularly punctuation and certain expressions

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

    end_of_turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kepem
    -0.42
     isNameExpr
    -0.34
     swój
    -0.33
     liderazgo
    -0.31
    epresidente
    -0.30
     σχέ
    -0.30
     Sna
    -0.30
     producenta
    -0.30
    にあります
    -0.30
    での
    -0.29
    POSITIVE LOGITS
     للاسماء
    0.67
    enderror
    0.63
    们
    0.63
    們
    0.62
    Datuak
    0.59
    AddTagHelper
    0.59
     esternos
    0.58
    новништво
    0.57
    MethodManager
    0.57
    ondissement
    0.56
    Act Density 0.291%

    No Known Activations