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

    Neuronpedia

    INDEX
    Explanations

    style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cavern
    -0.07
     PPP
    -0.07
     innocent
    -0.07
     encountering
    -0.07
    縣
    -0.07
    Seleccione
    -0.07
     Innoc
    -0.07
    <!--[
    -0.07
    Ca
    -0.06
     無
    -0.06
    POSITIVE LOGITS
     style
    0.16
     Style
    0.14
     styles
    0.12
    style
    0.12
    Style
    0.11
    -style
    0.11
     Styles
    0.11
     STYLE
    0.10
    STYLE
    0.10
    /style
    0.10
    Act Density 0.036%

    No Known Activations