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

    Neuronpedia

    INDEX
    Explanations

    forced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Welt
    -0.07
     uncommon
    -0.07
    (Task
    -0.06
     operated
    -0.06
     tattoos
    -0.06
     Equation
    -0.06
    版
    -0.06
     любой
    -0.06
     wedge
    -0.06
     پژوهش
    -0.06
    POSITIVE LOGITS
     ud
    0.07
    gear
    0.06
     ¿
    0.06
    ittance
    0.06
     Iraqi
    0.06
    AutoSize
    0.06
    мотр
    0.06
     Shack
    0.06
     diabetes
    0.06
    \param
    0.06
    Act Density 0.010%

    No Known Activations