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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     podemos
    -0.06
    _ok
    -0.06
     exclusively
    -0.06
    (date
    -0.06
    анием
    -0.06
     JACK
    -0.06
     POINT
    -0.06
     kterého
    -0.06
    hausen
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     screenplay
    0.07
    _ALWAYS
    0.06
    [${
    0.06
    verified
    0.06
     misdemean
    0.06
    extended
    0.06
    upertino
    0.06
     +**************
    0.06
     playlist
    0.06
    ==$
    0.06
    Act Density 0.003%

    No Known Activations