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

    Neuronpedia

    INDEX
    Explanations

    friends call me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ៣
    0.67
    Fmat
    0.64
    lanır
    0.57
     HNO
    0.52
    CRT
    0.51
     эпоху
    0.50
    Ḩ
    0.50
    TIMESTAMPDIFF
    0.49
    Chaer
    0.49
    ESTAMP
    0.48
    POSITIVE LOGITS
     trading
    0.52
     production
    0.44
     and
    0.43
     oder
    0.43
     o
    0.42
    ised
    0.42
     der
    0.42
     character
    0.42
     t
    0.41
     Trading
    0.40
    Act Density 0.009%

    No Known Activations