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

    Neuronpedia

    INDEX
    Explanations

    current date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     로그
    0.76
     log
    0.71
    Log
    0.70
     রজ
    0.69
    EARCH
    0.68
     সারা
    0.68
     rep
    0.67
     Log
    0.67
    loga
    0.65
    iciona
    0.65
    POSITIVE LOGITS
    flip
    0.61
    flipped
    0.61
    먼
    0.60
    帽
    0.60
     flip
    0.59
    交易所
    0.59
     Bruder
    0.59
     확
    0.58
    किया
    0.57
     verpflichtet
    0.56
    Act Density 0.181%

    No Known Activations