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

    Neuronpedia

    INDEX
    Explanations

    Website articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    阶段
    -0.06
     процесс
    -0.06
     verdad
    -0.06
     conducts
    -0.06
    475
    -0.06
    _bb
    -0.06
     Benn
    -0.06
     использу
    -0.06
     faulty
    -0.06
    _gender
    -0.06
    POSITIVE LOGITS
    .assertIn
    0.07
    playlist
    0.07
    ��
    0.07
     cazzo
    0.07
    .Dispose
    0.07
    (separator
    0.06
    _COMPONENT
    0.06
    Https
    0.06
    :flex
    0.06
     unmist
    0.06
    Act Density 0.186%

    No Known Activations