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

    Neuronpedia

    INDEX
    Explanations

    legal professionals like advocates and lawyers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.84
     Б
    0.64
     hvilket
    0.61
     హ
    0.59
     డా
    0.58
     Baca
    0.55
    Algorithms
    0.55
    ayın
    0.54
     వారు
    0.54
     Is
    0.53
    POSITIVE LOGITS
    י
    0.89
    c
    0.87
    O
    0.84
    d
    0.83
    T
    0.80
    i
    0.78
    C
    0.78
    یر
    0.77
    X
    0.73
    ಿ
    0.73
    Act Density 0.002%

    No Known Activations