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

    Neuronpedia

    INDEX
    Explanations

    HTTP web requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uje
    0.96
    อย่าง
    0.89
    一
    0.89
    ра
    0.79
    ेटर
    0.79
    できる
    0.76
    変わ
    0.76
    รับ
    0.76
     अच्छा
    0.76
    تان
    0.76
    POSITIVE LOGITS
     on
    1.21
     propiedades
    0.87
    ↵
    0.87
     verr
    0.87
     y
    0.86
    ル
    0.84
     aulas
    0.79
     il
    0.78
     e
    0.78
     regalo
    0.77
    Act Density 0.000%

    No Known Activations