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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between elements within a technical or scientific context

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

    on the basis of or than did

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    下载附件
    -0.56
    IUrlHelper
    -0.56
    Whilst
    -0.56
     Whilst
    -0.55
     perchè
    -0.55
    SequentialGroup
    -0.54
     Amongst
    -0.54
     whilst
    -0.53
     amongst
    -0.52
     Firstly
    -0.49
    POSITIVE LOGITS
    ​—
    0.49
     lät
    0.41
    ϫ
    0.40
    Rptr
    0.40
    さまざまな
    0.40
    AUTOR
    0.39
    Ϫ
    0.39
     Meri
    0.39
    ϭ
    0.38
    さまざま
    0.37
    Act Density 1.361%

    No Known Activations