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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and encouragement

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

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.63
    iſen
    -0.59
    ſchaft
    -0.54
    -0.54
    ſcher
    -0.53
    تقاوى
    -0.52
     autorytatywna
    -0.52
     geſch
    -0.50
     كومونز
    -0.50
    σιμοποι
    -0.50
    POSITIVE LOGITS
     haja
    0.40
    netinet
    0.37
     ayude
    0.37
     خیر
    0.34
    AccessorTable
    0.34
    urlopen
    0.33
    UseVisualStyle
    0.33
    Gruß
    0.33
    InBytes
    0.33
     protoimpl
    0.33
    Act Density 0.029%

    No Known Activations