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

    Neuronpedia

    INDEX
    Explanations

    Actions/Processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monarchy
    -0.07
     periods
    -0.07
     BIND
    -0.07
     pregnancies
    -0.06
     Heg
    -0.06
     implies
    -0.06
     century
    -0.06
    调
    -0.06
     browsers
    -0.06
     autoimmune
    -0.06
    POSITIVE LOGITS
    股
    0.06
    ========↵
    0.06
     Receive
    0.06
    Rated
    0.06
    celain
    0.06
    Grab
    0.06
    (..
    0.06
     　　 　
    0.06
    .toast
    0.06
    (pin
    0.06
    Act Density 0.125%

    No Known Activations