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

    Neuronpedia

    INDEX
    Explanations

    jupiter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.84
    ל
    0.84
    ב
    0.78
    る
    0.76
    л
    0.76
    一
    0.75
     as
    0.70
    ה
    0.68
    尔
    0.68
    وا
    0.64
    POSITIVE LOGITS
     Decatur
    0.67
     gallium
    0.60
    㓞
    0.58
    ный
    0.57
    ेंबर
    0.56
    )))))
    0.55
    ید
    0.55
    இது
    0.55
    ophilus
    0.55
     pemilihan
    0.55
    Act Density 0.001%

    No Known Activations