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

    Neuronpedia

    INDEX
    Explanations

    anyone interacting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    軻
    1.14
    다
    1.13
    ា
    1.09
    お金
    1.07
    дения
    1.06
     phen
    1.05
    んだろう
    1.04
    おか
    1.03
    1.02
    けど
    1.02
    POSITIVE LOGITS
     пул
    1.01
    celikle
    0.98
    rée
    0.96
    રો
    0.93
    zen
    0.91
     partir
    0.91
     retreat
    0.91
    ڄ
    0.91
     allá
    0.90
    osit
    0.90
    Act Density 0.003%

    No Known Activations