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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gehört
    -0.06
     pulls
    -0.06
    Thirty
    -0.06
     tapes
    -0.06
    _SCREEN
    -0.06
     Multiple
    -0.06
     beds
    -0.06
    -priced
    -0.06
    ifty
    -0.06
    784
    -0.06
    POSITIVE LOGITS
    %'↵
    0.06
    (re
    0.06
    έργ
    0.06
    -----↵
    0.06
    ublik
    0.06
    aguay
    0.06
     гар
    0.06
    erval
    0.06
     mpl
    0.06
     RECEIVE
    0.06
    Act Density 0.019%

    No Known Activations