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

    Neuronpedia

    INDEX
    Explanations

    positive attributes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ceding
    0.82
     யான
    0.68
    rous
    0.67
    ERIAL
    0.67
     Delta
    0.66
    றை
    0.66
     Holiday
    0.66
     மேலும்
    0.66
     Excellency
    0.65
     Два
    0.65
    POSITIVE LOGITS
     nonparametric
    0.76
     isot
    0.72
    亍
    0.67
     บน
    0.67
     on
    0.65
     Schra
    0.65
    บน
    0.64
     Schne
    0.64
     জীবনী
    0.64
    秣
    0.64
    Act Density 0.010%

    No Known Activations