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

    Neuronpedia

    INDEX
    Explanations

    directly applied styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ிர
    0.54
    *
    0.47
    YAN
    0.45
    icleta
    0.44
     Entire
    0.41
     dependencies
    0.41
    TI
    0.40
     Dependencies
    0.38
    **
    0.38
     Hass
    0.38
    POSITIVE LOGITS
     เนาะ
    0.52
     putih
    0.49
    ळे
    0.48
     vicino
    0.47
    سٹم
    0.47
    ahraga
    0.46
    ondale
    0.46
    𒆷
    0.45
     ۔
    0.45
     دیں
    0.44
    Act Density 0.003%

    No Known Activations