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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Det
    1.01
    DET
    0.95
    Det
    0.94
     DET
    0.92
     det
    0.87
    det
    0.81
     enriqu
    0.77
     detainees
    0.77
     GPU
    0.77
     নাহি
    0.76
    POSITIVE LOGITS
     hours
    0.87
     treaties
    0.77
    hours
    0.75
     hrs
    0.74
     outlook
    0.71
     הולנד
    0.71
     ساعت
    0.71
     wear
    0.70
     आव
    0.69
     आयुर्वेदिक
    0.69
    Act Density 0.000%

    No Known Activations