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

    Neuronpedia

    INDEX
    Explanations

    code/tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crime
    -0.07
     masa
    -0.07
    Domin
    -0.06
    "-
    -0.06
    (Project
    -0.06
     creams
    -0.06
    láš
    -0.06
     arena
    -0.06
     templ
    -0.06
    usuario
    -0.06
    POSITIVE LOGITS
    \View
    0.08
     regimes
    0.07
    *w
    0.07
    \Migrations
    0.07
    -instance
    0.07
    δυ
    0.06
    .annotations
    0.06
    ple
    0.06
     nour
    0.06
    vice
    0.06
    Act Density 0.004%

    No Known Activations