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

    Neuronpedia

    INDEX
    Explanations

    the word "style" or "styles"

    oai_token-act-pair · gemini-2.0-flash

    style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     style
    -2.63
     Style
    -2.41
    Style
    -2.36
    style
    -2.34
     STYLE
    -2.20
     styles
    -2.14
    STYLE
    -2.13
     estilo
    -1.94
     Styles
    -1.80
     스타일
    -1.76
    POSITIVE LOGITS
    Ț
    0.50
    itext
    0.47
    JNIEnv
    0.47
    Else
    0.47
    thold
    0.47
    除
    0.47
    PreExecute
    0.46
     consentimiento
    0.44
    osene
    0.43
    ocytes
    0.42
    Act Density 0.497%

    No Known Activations