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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    銀
    -0.07
     шкі
    -0.07
     �
    -0.06
    鋼
    -0.06
    Doctors
    -0.06
     redistributed
    -0.06
     Sender
    -0.06
     чим
    -0.06
    ابقه
    -0.06
     alice
    -0.06
    POSITIVE LOGITS
    (auth
    0.07
    [new
    0.06
    �
    0.06
    Electronic
    0.06
     Terminator
    0.06
    (success
    0.06
    (datas
    0.06
    iny
    0.06
    (album
    0.06
    xo
    0.06
    Act Density 0.000%

    No Known Activations