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

    Neuronpedia

    INDEX
    Explanations

    options at different price points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਾ
    0.59
    ла
    0.51
    не
    0.51
    异步
    0.48
    надцать
    0.46
     accueill
    0.46
    ми
    0.46
     বিজ্ঞ
    0.46
     приложение
    0.45
     完全
    0.44
    POSITIVE LOGITS
    Thailand
    0.64
    Ys
    0.63
    U
    0.62
    Wales
    0.61
    European
    0.59
    Japanese
    0.58
    Irish
    0.58
    E
    0.58
    Fair
    0.57
    F
    0.57
    Act Density 0.000%

    No Known Activations