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

    Neuronpedia

    INDEX
    Explanations

    software repositories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clin
    -0.07
    铯
    -0.07
    ㎛
    -0.07
    갬
    -0.07
    杷
    -0.07
    장애인
    -0.07
     uczniów
    -0.07
     czł
    -0.07
     PropelException
    -0.07
     eminent
    -0.07
    POSITIVE LOGITS
     Register
    0.08
     narrative
    0.07
     Open
    0.07
     нашего
    0.07
     Later
    0.07
    laden
    0.07
    财
    0.07
    灏
    0.06
     pada
    0.06
    	Session
    0.06
    Act Density 0.001%

    No Known Activations