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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    риз
    -0.07
     polygons
    -0.06
     Rug
    -0.06
     dó
    -0.06
    новаж
    -0.06
     дра
    -0.06
     bourbon
    -0.05
     Пра
    -0.05
     poč
    -0.05
    uální
    -0.05
    POSITIVE LOGITS
     *)↵
    0.07
    aşa
    0.07
    Components
    0.07
     #@
    0.07
     Nichols
    0.07
     leth
    0.07
     Reserve
    0.07
     Fortress
    0.06
    IELDS
    0.06
     #####
    0.06
    Act Density 0.000%

    No Known Activations