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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشاكل
    -0.09
    conditions
    -0.09
    controls
    -0.09
     يوجد
    -0.08
    eselect
    -0.08
    Seleccion
    -0.08
    jango
    -0.08
    initializer
    -0.08
     indifer
    -0.08
     Такие
    -0.08
    POSITIVE LOGITS
     shining
    0.08
    涓
    0.08
     badge
    0.08
     weave
    0.08
     electricity
    0.08
     glaciers
    0.08
     Electricity
    0.08
    塔
    0.08
     confer
    0.08
    Kd
    0.08
    Act Density 0.043%

    No Known Activations