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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "per" and its variations, indicating a focus on expressions involving rates, ratios, or divisions

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

    prefix per-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ilmu
    -0.53
    Hostname
    -0.47
     Komunikasi
    -0.47
    Azul
    -0.46
    ImageData
    -0.44
    tacte
    -0.44
     Monfieur
    -0.43
     itſelf
    -0.43
    cluso
    -0.42
    chaus
    -0.42
    POSITIVE LOGITS
     per
    1.85
     Per
    1.62
    Per
    1.42
     PER
    1.32
    per
    1.31
    PER
    1.02
     Perkin
    0.97
     Perkins
    0.89
     Peri
    0.89
     Perr
    0.86
    Act Density 0.026%

    No Known Activations