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

    Neuronpedia

    INDEX
    Explanations

    Save the code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     useEffect
    0.39
     executed
    0.38
     execute
    0.38
     parameter
    0.37
     použí
    0.37
     common
    0.37
     used
    0.36
     phase
    0.35
     circumstance
    0.35
     null
    0.35
    POSITIVE LOGITS
     above
    0.65
    Above
    0.61
     powy
    0.60
    上面的
    0.59
    上記
    0.58
     Above
    0.57
    above
    0.57
     acima
    0.57
     diatas
    0.56
    上記の
    0.56
    Act Density 0.003%

    No Known Activations