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

    Neuronpedia

    INDEX
    Explanations

    styles and styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dometer
    0.38
    numericUpDown
    0.37
    캣
    0.37
    ្ម
    0.36
     മത
    0.35
    槛
    0.35
    eeq
    0.34
    뿍
    0.34
    spf
    0.33
    setImageResource
    0.33
    POSITIVE LOGITS
     style
    3.92
     Style
    3.67
    Style
    3.53
     styles
    3.53
     estilo
    3.48
    style
    3.47
     스타일
    3.44
     стиль
    3.34
     стиля
    3.31
     Styles
    3.30
    Act Density 0.190%

    No Known Activations