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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain formatting symbols

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

    determines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.41
    DataSetChanged
    -0.33
    stdarg
    -0.32
     ioutil
    -0.31
    LayoutPanel
    -0.31
     onBackPressed
    -0.30
    valid
    -0.29
    canestro
    -0.29
    scope
    -0.29
    adalajara
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.71
    ########.
    0.62
    0.61
    Autoritní
    0.60
     kaarangay
    0.59
     تضيفلها
    0.57
    Datuak
    0.57
    Jîn
    0.54
    Morfo
    0.52
    хьтан
    0.50
    Act Density 0.036%

    No Known Activations