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

    Neuronpedia

    INDEX
    Explanations

    sys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fragmentation
    -0.07
    ’hui
    -0.07
     endanger
    -0.07
    Century
    -0.07
    portun
    -0.06
    isté
    -0.06
     appropri
    -0.06
    -cycle
    -0.06
     tort
    -0.06
    istique
    -0.06
    POSITIVE LOGITS
     invoke
    0.07
    (())↵
    0.06
    ...)↵
    0.06
    ....
    0.06
     Boise
    0.06
     انگلیسی
    0.06
     SDLK
    0.06
    关键
    0.06
     submerged
    0.06
     didFinish
    0.06
    Act Density 0.001%

    No Known Activations