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

    Neuronpedia

    INDEX
    Explanations

    conditional or random actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    徝
    0.46
    ut
    0.43
     dienen
    0.43
     ny
    0.42
    盽
    0.41
    ਡੇ
    0.41
    nehmer
    0.41
    ım
    0.41
    ール
    0.40
     дальнейшем
    0.39
    POSITIVE LOGITS
    вери
    0.50
    Quad
    0.44
     gratuita
    0.44
    ника
    0.42
    Quadr
    0.40
    CCCC
    0.40
    Quadrant
    0.40
     Pusat
    0.39
    이자
    0.38
     gratuito
    0.38
    Act Density 0.001%

    No Known Activations