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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     человеч
    -0.06
    kovi
    -0.06
    culus
    -0.05
    openhagen
    -0.05
    eu
    -0.05
    ECH
    -0.05
    /web
    -0.05
     repeatedly
    -0.05
    .rpm
    -0.05
    (am
    -0.05
    POSITIVE LOGITS
     #{
    0.07
    (!_
    0.07
     ting
    0.07
     demographic
    0.07
     со
    0.07
    抽
    0.07
    感
    0.07
     lover
    0.07
     triang
    0.07
    の一
    0.07
    Act Density 0.002%

    No Known Activations