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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SOFTWARE
    -0.07
     Valerie
    -0.06
    -cent
    -0.06
     CONTRIBUTORS
    -0.06
    uter
    -0.06
    .environ
    -0.06
     سنگ
    -0.06
    -President
    -0.06
    Ey
    -0.06
     hypers
    -0.06
    POSITIVE LOGITS
     Checkout
    0.07
     userDetails
    0.07
    .filter
    0.07
     Scene
    0.06
     Locate
    0.06
    ungi
    0.06
     mex
    0.06
    ceso
    0.06
    iễn
    0.06
     Tampa
    0.06
    Act Density 0.030%

    No Known Activations