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

    Neuronpedia

    INDEX
    Explanations

    mistake or error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blank
    -0.28
    æĮ¡
    -0.26
    é»ij马
    -0.26
    çī©
    -0.26
    å®ŀä½ĵ
    -0.26
    pivot
    -0.25
    çĻ½è¡£
    -0.25
    blank
    -0.25
     Deals
    -0.25
    ãģĦãģŁãģłãģı
    -0.25
    POSITIVE LOGITS
    ç½ijåıĭè¯Ħ论
    0.26
    满äºĨ
    0.25
    elseif
    0.25
    人å¿ĥ
    0.25
     forall
    0.25
    å¡ŀ
    0.24
    并ä¸İ
    0.24
     exhausting
    0.24
    endif
    0.23
     Pg
    0.23
    Act Density 2.304%

    No Known Activations