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

    Neuronpedia

    INDEX
    Explanations

    Dr. and MD titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.73
    er
    0.65
    on
    0.60
    l
    0.60
    as
    0.59
    at
    0.59
    al
    0.57
    n
    0.57
    h
    0.57
    ገልግሎ
    0.54
    POSITIVE LOGITS
     who
    0.71
     quien
    0.70
     الذين
    0.68
     in
    0.64
    ։
    0.58
     ktorí
    0.57
     σε
    0.56
    দের
    0.55
     quienes
    0.55
     pediatrician
    0.54
    Act Density 0.019%

    No Known Activations