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

    Neuronpedia

    INDEX
    Explanations

    the end of paragraphs or logical units in a text

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

    in the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.45
     wyg
    -0.34
    CppMethod
    -0.33
     vara
    -0.32
    IRED
    -0.32
    UpInside
    -0.32
     planas
    -0.31
    ఔ
    -0.31
    OnTop
    -0.31
     Prid
    -0.30
    POSITIVE LOGITS
     فريبيس
    0.71
    bootstrapcdn
    0.61
    \{\\
    0.51
     ujednoznacz
    0.51
    ModelAdmin
    0.50
     StatelessWidget
    0.49
    ConstraintMaker
    0.49
     Gelder
    0.47
     zuſammen
    0.46
    IntoConstraints
    0.46
    Act Density 0.288%

    No Known Activations