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

    Neuronpedia

    INDEX
    Explanations

    stamps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NT
    -0.08
    (x
    -0.07
     Nguyen
    -0.07
     dynam
    -0.07
     teen
    -0.07
    (Syntax
    -0.07
    .Y
    -0.07
     tranny
    -0.07
    ember
    -0.06
     Energy
    -0.06
    POSITIVE LOGITS
    *>&
    0.07
     accelerated
    0.07
    Replacing
    0.06
    ível
    0.06
    坚守
    0.06
     hiểu
    0.06
    Productos
    0.06
    这个时代
    0.06
    opro
    0.06
    㽏
    0.06
    Act Density 0.008%

    No Known Activations