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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "ご"

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

    polite prefix ご

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.35
    basically
    -0.34
    domada
    -0.32
     basically
    -0.32
    Basically
    -0.31
    n
    -0.31
     Schluss
    -0.30
     ordinateur
    -0.30
    secuencias
    -0.29
    毛病
    -0.29
    POSITIVE LOGITS
    ご
    2.42
     ご
    1.67
    のご
    1.55
    をご
    1.43
    にご
    1.38
    でご
    1.33
    御
    1.09
    ご理解
    0.82
     御
    0.82
     nakalista
    0.81
    Act Density 0.004%

    No Known Activations