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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and correctness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಮ
    0.63
    મ
    0.60
    ра
    0.59
    ना
    0.59
    স
    0.57
    ச
    0.57
    ا
    0.56
    সিস
    0.55
    জ
    0.54
    ల
    0.54
    POSITIVE LOGITS
     to
    0.58
    II
    0.57
    VP
    0.52
     behandling
    0.52
     pemas
    0.52
    ét
    0.51
     memiliki
    0.51
     speichern
    0.51
     apabila
    0.50
     codec
    0.50
    Act Density 0.000%

    No Known Activations