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

    Neuronpedia

    INDEX
    Explanations

    subscription limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Show
    -0.09
    @$
    -0.06
    Found
    -0.06
    /connection
    -0.06
     controller
    -0.06
     Buk
    -0.06
    tower
    -0.06
    workers
    -0.06
    Registrar
    -0.06
     Basil
    -0.06
    POSITIVE LOGITS
    简
    0.07
     тра
    0.07
    inja
    0.07
     lược
    0.07
    otp
    0.06
     특
    0.06
    (actions
    0.06
    ери
    0.06
     Куб
    0.06
     Flint
    0.06
    Act Density 0.003%

    No Known Activations