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

    Neuronpedia

    INDEX
    Explanations

    adjud

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iore
    -0.08
     evoke
    -0.07
    utations
    -0.07
    гу
    -0.07
     magnificent
    -0.07
    Grand
    -0.07
    (flow
    -0.07
     tolerate
    -0.07
    north
    -0.07
    "path
    -0.07
    POSITIVE LOGITS
     adjud
    0.08
     encryption
    0.08
     economies
    0.07
    ﱉ
    0.07
     stripping
    0.06
     connector
    0.06
    altet
    0.06
     PackageManager
    0.06
    暿
    0.06
     disables
    0.06
    Act Density 0.001%

    No Known Activations