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

    Neuronpedia

    INDEX
    Explanations

    New Delhi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    その
    0.75
     jadi
    0.74
    Z
    0.74
     absor
    0.73
    場合がございます
    0.72
     นะ
    0.71
     dirige
    0.70
    Ihr
    0.70
    ご利用
    0.69
    ੍ਰ
    0.68
    POSITIVE LOGITS
     tume
    0.79
    coconut
    0.79
    ی
    0.77
    цкі
    0.77
     местах
    0.76
    ්
    0.75
     Prony
    0.75
     चंद
    0.74
     Senado
    0.73
     друзей
    0.73
    Act Density 0.001%

    No Known Activations