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

    Neuronpedia

    INDEX
    Explanations

    what seems to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seen
    0.54
     certes
    0.49
    seen
    0.48
     seeming
    0.47
     undoubtedly
    0.46
    obviously
    0.46
     фактически
    0.46
     طبعا
    0.46
     seemed
    0.46
    seem
    0.44
    POSITIVE LOGITS
     awfully
    0.63
     khá
    0.52
    不错的
    0.52
     judging
    0.52
     довольно
    0.52
     effortlessly
    0.52
     🤔
    0.51
     oddly
    0.50
     quite
    0.47
     ziemlich
    0.47
    Act Density 0.020%

    No Known Activations