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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pub
    -0.08
     hacked
    -0.07
     emin
    -0.07
     Ikea
    -0.07
     landscapes
    -0.07
     Widget
    -0.06
     continents
    -0.06
     schem
    -0.06
     Î
    -0.06
    空
    -0.06
    POSITIVE LOGITS
    ولي
    0.07
    َج
    0.06
    agher
    0.06
    ρε
    0.06
    .school
    0.06
    _HPP
    0.06
    zę
    0.06
    IntervalSince
    0.06
    gue
    0.06
    *g
    0.06
    Act Density 0.049%

    No Known Activations