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

    Neuronpedia

    INDEX
    Explanations

    periods after numbers or symbols, sometimes with preceding text

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    όνι
    -0.45
    定
    -0.45
    beelding
    -0.44
     MERCHANTABILITY
    -0.43
    喫
    -0.42
    -
    -0.42
    ce
    -0.41
     esta
    -0.40
     kekerasan
    -0.40
    ǎ
    -0.40
    POSITIVE LOGITS
    OGND
    0.90
     Савезне
    0.75
    tagHelperRunner
    0.72
    featureID
    0.72
     دیکھیے
    0.69
    ंदीखरीदारी
    0.68
    intios
    0.65
    TagMode
    0.65
     nahilalakip
    0.64
     تضيفلها
    0.63
    Act Density 1.223%

    No Known Activations