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

    Neuronpedia

    INDEX
    Explanations

    Math concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    omi
    -0.08
    _be
    -0.07
    parameters
    -0.07
    око
    -0.07
     bóng
    -0.07
     Hunts
    -0.07
     Pax
    -0.07
     resurrection
    -0.06
     Suz
    -0.06
     Hole
    -0.06
    POSITIVE LOGITS
     DECL
    0.06
     ();
    0.06
    (blog
    0.06
     imagine
    0.06
    beautiful
    0.06
    DECL
    0.06
     Росії
    0.06
    .www
    0.06
     обра
    0.06
    ท
    0.06
    Act Density 0.102%

    No Known Activations