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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain punctuation, particularly full stops and commas

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

    end of sentence or clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     היתה
    -0.41
    ">(</
    -0.39
    CJK
    -0.37
    теристика
    -0.36
    AndGet
    -0.32
    Và
    -0.32
     hoja
    -0.32
    awah
    -0.32
    ernalia
    -0.31
    sikker
    -0.30
    POSITIVE LOGITS
    WriteTagHelper
    0.72
    tvguidetime
    0.70
     snippetHide
    0.66
    ésultats
    0.61
     queſta
    0.60
    RTSC
    0.60
     ब्रेकडाउन
    0.59
    WriteBarrier
    0.59
     HasFactory
    0.58
    sizeCache
    0.57
    Act Density 0.137%

    No Known Activations