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

    Neuronpedia

    INDEX
    Explanations

    des

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ill
    -0.07
     dipl
    -0.07
    泉
    -0.07
     acceler
    -0.07
    inston
    -0.07
    良好的
    -0.07
    爬
    -0.07
     baiser
    -0.07
    Pot
    -0.07
     boolean
    -0.06
    POSITIVE LOGITS
    됐
    0.07
    ctors
    0.07
    下載
    0.07
    texts
    0.07
     towing
    0.07
    檩
    0.07
    续
    0.07
    acts
    0.07
    ButtonText
    0.07
     Lịch
    0.07
    Act Density 0.017%

    No Known Activations