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

    Neuronpedia

    INDEX
    Explanations

    numerical and measurement-related terms in descriptions of products

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

    special characters and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.43
    toThrow
    -0.42
    complexContent
    -0.40
     Crawford
    -0.39
    MouseEvent
    -0.35
     Clay
    -0.35
    createTextNode
    -0.35
     Wright
    -0.34
    ol
    -0.34
    summary
    -0.34
    POSITIVE LOGITS
     pleaſure
    0.63
     houſe
    0.56
     itſelf
    0.56
    انتهای
    0.55
     Normdatei
    0.54
     juſ
    0.54
     ſtand
    0.52
     ſte
    0.51
    IVEREF
    0.49
     Infórmanos
    0.49
    Act Density 0.007%

    No Known Activations