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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols, particularly quotation marks and dollar signs

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

    bracketed words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     özellikle
    -0.50
    SequentialGroup
    -0.49
     specifically
    -0.47
     różne
    -0.47
     biasa
    -0.45
     kaynağından
    -0.45
    AnchorStyles
    -0.44
    ientôt
    -0.44
     khusus
    -0.44
     Haare
    -0.43
    POSITIVE LOGITS
     للمعارف
    0.66
     ſche
    0.57
    XmlAccessorType
    0.56
     című
    0.54
     ſtate
    0.52
     roller
    0.51
    erker
    0.50
     antim
    0.50
     ſta
    0.50
     queſta
    0.49
    Act Density 0.103%

    No Known Activations