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

    Neuronpedia

    INDEX
    Explanations

    `[`

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unable
    -0.07
     nějak
    -0.07
    (play
    -0.06
     lol
    -0.06
    lep
    -0.06
     آمریک
    -0.06
    ��
    -0.06
     unintended
    -0.06
     такого
    -0.06
     πε
    -0.06
    POSITIVE LOGITS
    урс
    0.07
    .ur
    0.07
    _mass
    0.07
    ATALOG
    0.06
    Listening
    0.06
     ACTION
    0.06
    openhagen
    0.06
    (cursor
    0.06
     مسئ
    0.06
     قطر
    0.06
    Act Density 0.001%

    No Known Activations