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

    Neuronpedia

    INDEX
    Explanations

    win

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }(
    -0.07
    slide
    -0.06
    зна
    -0.06
    ,),↵
    -0.06
    ),
↵
    -0.06
    isspace
    -0.06
     個
    -0.06
     cosplay
    -0.06
     přib
    -0.06
    BeforeEach
    -0.06
    POSITIVE LOGITS
    sidebar
    0.07
     سپتامبر
    0.06
     attributed
    0.06
     lifts
    0.06
    thern
    0.06
     الح
    0.06
    rám
    0.06
    št
    0.06
    国家
    0.06
     относят
    0.06
    Act Density 0.118%

    No Known Activations