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

    Neuronpedia

    INDEX
    Explanations

    questions starting with what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是否有
    1.31
    是否
    1.24
     是否
    1.18
     how
    1.17
     શું
    1.08
     apakah
    1.07
     specific
    1.07
    specific
    1.07
     whether
    1.07
    能否
    1.06
    POSITIVE LOGITS
     من
    0.79
     في
    0.71
     Through
    0.69
     For
    0.68
     أ
    0.64
     through
    0.61
     Following
    0.60
     على
    0.60
     And
    0.60
     But
    0.58
    Act Density 0.105%

    No Known Activations