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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    謗
    0.80
    뻥
    0.77
     certainty
    0.75
    IFIED
    0.74
    abbing
    0.74
     यूं
    0.73
     နဲ့
    0.73
     innings
    0.73
     таъ
    0.73
     वैसे
    0.73
    POSITIVE LOGITS
     deleted
    0.72
    nodemailer
    0.70
    cans
    0.69
    ালো
    0.69
     tib
    0.69
     cans
    0.67
    匚
    0.67
    -_
    0.67
     seper
    0.66
     awaited
    0.66
    Act Density 0.063%

    No Known Activations