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

    Neuronpedia

    INDEX
    Explanations

    geometry diagonals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     critique
    -0.08
    েস্ক
    -0.08
     ganó
    -0.07
     overhaul
    -0.07
     Atmospheric
    -0.07
     retired
    -0.07
    /The
    -0.07
     EBITDA
    -0.07
    -green
    -0.07
     retire
    -0.07
    POSITIVE LOGITS
    sense
    0.09
     perfectamente
    0.08
     sentido
    0.08
     sense
    0.08
     atención
    0.07
     langen
    0.07
    bk
    0.07
    Bezier
    0.07
     sentidos
    0.07
    割
    0.07
    Act Density 0.025%

    No Known Activations