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

    Neuronpedia

    INDEX
    Explanations

    assertions or questions regarding doubts and confirmations

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

    yes no false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.47
     okuyayım
    -0.36
    EndProject
    -0.33
    ftagPool
    -0.33
    ########.
    -0.32
    最快更新
    -0.31
     purposes
    -0.30
    ⤹
    -0.30
     Mahl
    -0.30
    Elő
    -0.29
    POSITIVE LOGITS
    AnchorStyles
    0.61
     ujednoznacz
    0.60
    存于互联网档案馆
    0.54
     للمعارف
    0.51
    ьаж
    0.50
     الرياضيه
    0.50
    Искәрмәләр
    0.49
    ंदीखरीदारी
    0.48
    LookAnd
    0.47
    าสตร์
    0.47
    Act Density 0.123%

    No Known Activations