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

    Neuronpedia

    INDEX
    Explanations

    BBC News

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ന്തപു
    0.94
    蹉
    0.93
    型的
    0.87
     নদী
    0.87
    orma
    0.86
    atum
    0.86
    QUOTE
    0.86
     telefonu
    0.85
    ivist
    0.85
    នូវ
    0.84
    POSITIVE LOGITS
    taro
    0.81
     isso
    0.77
     Orang
    0.76
     Wakil
    0.76
     sikker
    0.75
    ψει
    0.72
    지로
    0.71
     menjadi
    0.71
    ය
    0.71
     Wird
    0.71
    Act Density 0.005%

    No Known Activations