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

    Neuronpedia

    INDEX
    Explanations

    music styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solely
    0.74
     gây
    0.69
    固
    0.66
     sole
    0.64
    每天
    0.62
    만
    0.61
     largely
    0.61
     cause
    0.61
     Sole
    0.60
    veh
    0.59
    POSITIVE LOGITS
    style
    1.66
     style
    1.53
     Style
    1.47
    Style
    1.46
    esque
    1.44
     estilo
    1.38
    type
    1.38
     STYLE
    1.31
    般的
    1.25
    式的
    1.25
    Act Density 0.713%

    No Known Activations