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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mohamed
    -0.07
    脑
    -0.07
    υ
    -0.07
     Satoshi
    -0.07
    著作權
    -0.07
    _RUNTIME
    -0.07
     Keeper
    -0.07
    {}↵↵
    -0.06
    Pane
    -0.06
     mt
    -0.06
    POSITIVE LOGITS
    PRECATED
    0.08
    _LS
    0.07
    legant
    0.07
    bursement
    0.07
    的努力
    0.07
     renew
    0.07
    structures
    0.07
     PRODUCTS
    0.06
     각
    0.06
    ircular
    0.06
    Act Density 0.043%

    No Known Activations