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

    Neuronpedia

    INDEX
    Explanations

    new words or codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    R
    0.90
     R
    0.90
     AA
    0.87
     EUR
    0.86
    AA
    0.84
     AUD
    0.83
    JA
    0.79
    HA
    0.78
     VA
    0.77
    AU
    0.76
    POSITIVE LOGITS
     nowego
    0.82
    新しい
    0.81
     neuen
    0.79
     جديد
    0.76
     جدید
    0.72
    .');
    0.71
    new
    0.71
     جديدة
    0.71
    ર્મ
    0.70
    retrieve
    0.70
    Act Density 0.000%

    No Known Activations