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

    Neuronpedia

    INDEX
    Explanations

    comparison or function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pdelay
    0.48
    ূল্য
    0.44
     серде
    0.44
    ลล์
    0.44
     감소
    0.41
     ขั้น
    0.41
    ষ্
    0.41
    пад
    0.40
     esté
    0.40
     αφού
    0.40
    POSITIVE LOGITS
     gruppi
    0.45
    دهای
    0.45
     any
    0.44
     मोठे
    0.43
     serius
    0.43
    سور
    0.42
    gru
    0.42
    偶
    0.40
     sowohl
    0.40
     اقسام
    0.40
    Act Density 0.005%

    No Known Activations