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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating components or segments of a larger whole

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

    part of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.71
    ſelf
    -0.66
     itſelf
    -0.61
     ſch
    -0.58
    ſelves
    -0.58
     Perſ
    -0.58
    -0.57
     ſtate
    -0.56
     Eſ
    -0.55
     CascadeType
    -0.55
    POSITIVE LOGITS
     part
    0.48
    EditorBrowsable
    0.46
    的一部分
    0.44
    enumi
    0.43
    ThroughAttribute
    0.43
     Teil
    0.38
     ضمن
    0.36
     частью
    0.36
     initiative
    0.35
     بخشی
    0.35
    Act Density 0.022%

    No Known Activations