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

    Neuronpedia

    INDEX
    Explanations

    free followed by specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dı
    0.76
    Yb
    0.76
    景观
    0.75
    教
    0.72
     facet
    0.71
    mel
    0.70
    识别
    0.70
     fable
    0.69
    mega
    0.69
    ليز
    0.68
    POSITIVE LOGITS
    bies
    1.73
    bie
    1.66
    zers
    1.23
    zing
    1.22
    zes
    1.06
    form
    1.04
    keh
    1.04
    flowing
    1.02
    floating
    1.02
    bees
    1.01
    Act Density 0.090%

    No Known Activations