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

    Neuronpedia

    INDEX
    Explanations

    Tk

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.13
    e
    1.08
    i
    0.93
    iou
    0.92
    ו
    0.91
    iin
    0.90
    it
    0.90
    a
    0.89
    sterne
    0.87
    siege
    0.86
    POSITIVE LOGITS
     hapl
    0.82
     shampoos
    0.75
    薈
    0.74
     plaster
    0.74
     نړ
    0.74
     hiker
    0.73
     grot
    0.73
     shelters
    0.73
     datasets
    0.73
     하다
    0.73
    Act Density 0.000%

    No Known Activations