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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     empty
    -0.08
    eras
    -0.06
     *)"
    -0.06
     selects
    -0.06
    five
    -0.06
    unta
    -0.06
     slogans
    -0.06
     consts
    -0.06
     feasible
    -0.06
    Email
    -0.06
    POSITIVE LOGITS
     kab
    0.07
     allied
    0.06
    abbage
    0.06
     بي
    0.06
     Homepage
    0.06
     vent
    0.06
    agues
    0.06
    양
    0.06
     někter
    0.06
    LOGY
    0.06
    Act Density 0.034%

    No Known Activations