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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to measurements and statistics

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

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Finlandia
    -0.56
     Chrift
    -0.53
    ſelf
    -0.52
    ſelves
    -0.49
     Jefus
    -0.49
    glLoad
    -0.46
    niksi
    -0.46
    ťaž
    -0.46
    URLConnection
    -0.45
    Xna
    -0.45
    POSITIVE LOGITS
     فريبيس
    0.49
     Eier
    0.46
     Soe
    0.41
    ptid
    0.40
     Heer
    0.40
    ussch
    0.39
    بوابة
    0.39
     Ewig
    0.38
    GEBURTS
    0.38
     Dalio
    0.38
    Act Density 0.131%

    No Known Activations