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

    Neuronpedia

    INDEX
    Explanations

    references to scientific concepts and processes

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

    information presented or obtained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.52
     CreateTagHelper
    -0.48
    toMatchSnapshot
    -0.39
    uxxxx
    -0.39
    żesz
    -0.39
    RenderAtEndOf
    -0.38
    addCriterion
    -0.37
    TypedDataSet
    -0.37
     للاسماء
    -0.36
    IntentFilter
    -0.36
    POSITIVE LOGITS
     announced
    0.83
     disampaikan
    0.81
     presented
    0.80
     publicada
    0.79
     offered
    0.78
     undertaken
    0.77
    announced
    0.74
     published
    0.74
     mentioned
    0.73
     obtained
    0.72
    Act Density 0.472%

    No Known Activations