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

    Neuronpedia

    INDEX
    Explanations

    CN followed by abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fatten
    0.45
    痘
    0.41
     Pern
    0.39
     ዋ
    0.39
     Pric
    0.38
     التلاميذ
    0.37
     ربعه
    0.37
     ගත
    0.36
     새벽
    0.36
    Broad
    0.35
    POSITIVE LOGITS
     CN
    0.98
     cn
    0.90
    CN
    0.89
    cn
    0.80
     Cn
    0.77
    Cn
    0.71
     CNT
    0.66
     CNN
    0.57
     cnv
    0.57
    CNN
    0.57
    Act Density 0.005%

    No Known Activations