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

    Neuronpedia

    INDEX
    Explanations

    efforts and failures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     δι
    -0.06
     ethn
    -0.06
    ゲ
    -0.06
    λλη
    -0.06
    poll
    -0.06
     iron
    -0.06
    _bm
    -0.06
     Dollar
    -0.06
     DH
    -0.06
     diarrhea
    -0.06
    POSITIVE LOGITS
     bestselling
    0.06
     хвилин
    0.06
    รร
    0.06
    ahaha
    0.06
     게시판
    0.06
     Trump
    0.06
     should
    0.06
    	setup
    0.06
     의해
    0.06
     eius
    0.06
    Act Density 0.097%

    No Known Activations