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

    Neuronpedia

    INDEX
    Explanations

    continues to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     continued
    0.51
     continual
    0.42
    continued
    0.42
     একই
    0.40
     intact
    0.39
    此
    0.39
     дальней
    0.39
     similar
    0.37
     maintain
    0.37
     upkeep
    0.37
    POSITIVE LOGITS
    Still
    0.57
    还是
    0.48
     ainda
    0.47
    الات
    0.45
    还没有
    0.44
     ancora
    0.44
    still
    0.44
     todavía
    0.43
    अभी
    0.43
     Still
    0.43
    Act Density 0.013%

    No Known Activations