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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sh
    -0.07
     fierce
    -0.07
     demand
    -0.06
     democracy
    -0.06
     Abrams
    -0.06
    unknown
    -0.06
     viruses
    -0.06
    ฮ
    -0.06
     vocational
    -0.06
     Airlines
    -0.06
    POSITIVE LOGITS
    -you
    0.07
    承
    0.06
    /sweetalert
    0.06
    Hint
    0.06
     há
    0.06
     словами
    0.06
    ับสน
    0.06
     EntryPoint
    0.06
    особ
    0.06
    (varargin
    0.06
    Act Density 0.090%

    No Known Activations