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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions and terms related to counting or measuring entities

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

    Follows "number of" or a synonym

    np_acts-logits-general · gemini-2.0-flash

    how many

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.46
     enfans
    -0.43
     renou
    -0.42
    CurrentValue
    -0.40
    verd
    -0.40
     cielos
    -0.39
     ★★★
    -0.39
     tournant
    -0.39
    dreams
    -0.38
     rêves
    -0.38
    POSITIVE LOGITS
    Aantal
    0.72
    Cuántos
    0.67
    有多少
    0.65
    NumberOf
    0.65
     noOf
    0.63
     počet
    0.58
     getNum
    0.57
     antal
    0.57
     jumlah
    0.56
     Fewer
    0.56
    Act Density 0.376%

    No Known Activations