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

    Neuronpedia

    INDEX
    Explanations

    starts with es

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ciebie
    0.44
    ahooks
    0.44
    徸
    0.43
    瀧
    0.43
     outcrops
    0.40
    <unused516>
    0.40
     सिंग
    0.38
    粎
    0.38
    ۴
    0.38
    getAbsolutePath
    0.38
    POSITIVE LOGITS
     ES
    0.85
     es
    0.80
    Es
    0.72
    ES
    0.69
    ESO
    0.69
     ESC
    0.68
     esc
    0.68
     Es
    0.68
     Esc
    0.67
    Esc
    0.66
    Act Density 0.017%

    No Known Activations