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

    Neuronpedia

    INDEX
    Explanations

    what happens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    launch
    0.77
    ots
    0.75
    mak
    0.68
    吐
    0.62
    ोट
    0.62
    les
    0.62
     launch
    0.62
     Founding
    0.61
    session
    0.61
    ot
    0.60
    POSITIVE LOGITS
     happens
    3.34
     happen
    3.31
     happened
    3.26
     happening
    2.98
     Happens
    2.87
     terjadi
    2.72
     occurs
    2.69
     Happened
    2.66
     occur
    2.64
     occurred
    2.58
    Act Density 0.134%

    No Known Activations