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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [\
    -0.07
    ��
    -0.07
     frei
    -0.07
     tut
    -0.07
    .Lo
    -0.07
    RICT
    -0.07
     única
    -0.07
     cz
    -0.07
    Legend
    -0.06
    umbn
    -0.06
    POSITIVE LOGITS
     Turtle
    0.06
    였
    0.06
    .ActionBar
    0.06
     HEADER
    0.06
    出版社
    0.06
    었
    0.06
    ambre
    0.06
     안내
    0.06
    _ble
    0.06
     بزر
    0.06
    Act Density 0.013%

    No Known Activations