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

    Neuronpedia

    INDEX
    Explanations

    finding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loc
    -0.07
    身上
    -0.07
    ,
↵
↵
    -0.06
     clutch
    -0.06
     sulfate
    -0.06
    962
    -0.06
    そう
    -0.06
     //}↵↵
    -0.06
     multitude
    -0.06
    門
    -0.06
    POSITIVE LOGITS
    uyền
    0.06
     держави
    0.06
    ческой
    0.06
     )"
    0.06
     الحل
    0.05
    iciary
    0.05
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.05
    .parseFloat
    0.05
     hotter
    0.05
     happier
    0.05
    Act Density 0.053%

    No Known Activations