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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    声音
    -0.07
    言わ
    -0.06
     scaled
    -0.06
    ��
    -0.06
    ancellation
    -0.06
    Thus
    -0.06
    深
    -0.06
     Checklist
    -0.06
     黄
    -0.06
     我
    -0.06
    POSITIVE LOGITS
    Implement
    0.07
     Evropy
    0.06
    oleč
    0.06
    (Cs
    0.06
    _win
    0.06
    Finished
    0.06
    _UNIQUE
    0.06
     gi
    0.06
     الشي
    0.06
    /pol
    0.06
    Act Density 0.353%

    No Known Activations