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

    Neuronpedia

    INDEX
    Explanations

    conversation further

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ْر
    0.81
    Ін
    0.81
    к
    0.78
     ş
    0.77
    єн
    0.77
    קה
    0.75
    ق
    0.74
    ຂອງ
    0.71
    CIP
    0.71
    INGO
    0.71
    POSITIVE LOGITS
     नम्बर
    0.94
     Wend
    0.80
     mittens
    0.79
     الزمن
    0.76
     গতকাল
    0.75
     lids
    0.74
    ቹን
    0.72
    ajn
    0.72
    stituting
    0.71
    -(
    0.70
    Act Density 0.000%

    No Known Activations