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

    Neuronpedia

    INDEX
    Explanations

    special formatting or unusual white space characters in the text

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

    identifiers, legal jargon, and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.57
    RetentionPolicy
    -0.50
     lenker
    -0.48
     <>",
    -0.46
     propOrder
    -0.45
    يكب
    -0.45
    memoized
    -0.45
    DockStyle
    -0.44
    mybatisplus
    -0.44
    AnchorStyles
    -0.43
    POSITIVE LOGITS
    1.45
     للاسماء
    0.63
    
    0.58
    
    0.52
    devamını
    0.51
    
    0.51
    KommentareTeilen
    0.50
    
    0.50
    
    0.50
     дописавши
    0.49
    Act Density 0.002%

    No Known Activations