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

    Neuronpedia

    INDEX
    Explanations

    grids and squares

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marital
    -0.08
     distribution
    -0.08
    牢
    -0.07
    িষ্ঠ
    -0.07
     devi
    -0.07
     نجد
    -0.07
     dev
    -0.07
     المدار
    -0.07
    év
    -0.07
     affaires
    -0.07
    POSITIVE LOGITS
     எல்ல
    0.09
     переход
    0.09
     Boundary
    0.08
     Zwischen
    0.08
     નિર્ણ
    0.08
     kinderen
    0.08
    	End
    0.08
     தொடர்ந்து
    0.08
     விள
    0.08
    _boundary
    0.08
    Act Density 0.043%

    No Known Activations