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

    Neuronpedia

    INDEX
    Explanations

    fixed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outright
    -0.09
     balloons
    -0.09
    女子
    -0.08
    敗
    -0.08
    /table
    -0.08
     Touring
    -0.08
     balloon
    -0.08
     men
    -0.08
     tbl
    -0.08
     näytt
    -0.07
    POSITIVE LOGITS
    Physics
    0.08
     сайын
    0.08
     physics
    0.08
     خور
    0.08
     atualizar
    0.08
     biomechanics
    0.08
     العمل
    0.08
     predictable
    0.08
     والاج
    0.08
     discrete
    0.08
    Act Density 0.004%

    No Known Activations