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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InstanceState
    -0.49
     {.
    -0.46
     sen
    -0.45
    MeasureSpec
    -0.44
     Cre
    -0.43
     lade
    -0.43
    Xna
    -0.42
     thousands
    -0.42
    aarrggbb
    -0.41
     dozens
    -0.40
    POSITIVE LOGITS
    Portail
    0.68
    PARATUS
    0.65
     Савезне
    0.60
     mergeFrom
    0.60
     насељу
    0.58
     Jefus
    0.57
     Administrativna
    0.57
    NonQuery
    0.57
    Rujuakan
    0.56
     aikaa
    0.56
    Act Density 0.002%

    No Known Activations