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

    Neuronpedia

    INDEX
    Explanations

    internal states

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ہے۔
    0.47
     resulted
    0.46
     இருப்பது
    0.46
    があるので
    0.45
     jsou
    0.44
     ช่วย
    0.44
    都是
    0.44
     هستند
    0.44
     são
    0.44
     является
    0.44
    POSITIVE LOGITS
     perceive
    1.02
     want
    1.01
     feel
    0.97
     see
    0.88
     prefer
    0.88
     hesitate
    0.86
     realize
    0.84
     expect
    0.82
     hear
    0.80
     have
    0.80
    Act Density 0.283%

    No Known Activations