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

    Neuronpedia

    INDEX
    Explanations

    properties of subjects or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.58
    ED
    0.57
    "
    0.57
    CO
    0.54
    M
    0.51
    IL
    0.50
    t
    0.50
    cal
    0.49
     is
    0.49
    GB
    0.49
    POSITIVE LOGITS
    olni
    0.60
    𒅖
    0.53
     transaksi
    0.52
     منفی
    0.51
     ကု
    0.51
    संगिक
    0.49
     suku
    0.48
    *((*
    0.48
     vitth
    0.48
     APPE
    0.48
    Act Density 0.001%

    No Known Activations