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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and terms that enhance argumentation or elaboration in writing

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

    multilingual technical content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.49
    när
    -0.42
    醐
    -0.42
     gabbana
    -0.40
    gemaakt
    -0.38
    abstractmethod
    -0.38
     xrange
    -0.38
     bénéficient
    -0.36
    transQ
    -0.36
    emble
    -0.36
    POSITIVE LOGITS
    IntoConstraints
    0.47
    Бележки
    0.47
    …]
    0.46
     المعيارى
    0.45
     فريبيس
    0.42
    ...]
    0.41
     Wikiseite
    0.40
    DockStyle
    0.39
    >[]
    0.39
     Himo
    0.39
    Act Density 0.015%

    No Known Activations