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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or symbols, particularly related to financial or numerical contexts

    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
     autorytatywna
    -0.47
    UnusedPrivate
    -0.40
    !*\
    -0.39
    Linki
    -0.38
    RTGC
    -0.35
    appcompat
    -0.35
     piensa
    -0.34
    ModelBuilder
    -0.33
     Diſ
    -0.33
     quæ
    -0.33
    POSITIVE LOGITS
     كومونز
    0.48
    orrho
    0.47
     فريبيس
    0.47
    findpost
    0.46
    pielen
    0.45
    farer
    0.45
     Mariner
    0.44
    ⓧ
    0.44
    気になって
    0.43
     CHORUS
    0.43
    Act Density 0.514%

    No Known Activations