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

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases indicating methods or approaches

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

    in X ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kháu
    -0.47
    новништво
    -0.43
     ویکی‌پدی
    -0.42
    匿名使用者
    -0.39
     Italijani
    -0.37
     gyhoeddwyd
    -0.37
     industriel
    -0.36
    samt
    -0.35
     libere
    -0.35
    Rè
    -0.35
    POSITIVE LOGITS
    StoryboardSegue
    0.71
    LookAnd
    0.63
     arguably
    0.60
    发表于
    0.56
    一見
    0.54
     essentially
    0.52
    Essentially
    0.50
    ChildScrollView
    0.50
     rightly
    0.49
    LLocation
    0.49
    Act Density 0.012%

    No Known Activations