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

    Neuronpedia

    INDEX
    Explanations

    embedded within, energy analogy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ករណ៍
    0.50
    िसोदिया
    0.48
    वासीय
    0.46
    抔
    0.45
    衊
    0.45
    匽
    0.45
    tion
    0.44
     universit
    0.44
     итоге
    0.43
     weiteres
    0.43
    POSITIVE LOGITS
    :
    0.89
    4
    0.64
    7
    0.64
    6
    0.61
    8
    0.61
    5
    0.60
    9
    0.53
     ۴
    0.47
     d
    0.42
    ۔
    0.42
    Act Density 1.368%

    No Known Activations