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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Elim
    -0.07
     Hur
    -0.07
    _HANDLER
    -0.07
    ntl
    -0.07
     Dmit
    -0.07
    Serve
    -0.07
    供应
    -0.06
     Influence
    -0.06
     Serv
    -0.06
     Clinton
    -0.06
    POSITIVE LOGITS
     улыб
    0.07
     according
    0.07
     homicides
    0.07
    as
    0.07
    amos
    0.07
     as
    0.06
     只
    0.06
     According
    0.06
     ipsum
    0.06
    ังน
    0.06
    Act Density 0.011%

    No Known Activations