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

    Neuronpedia

    INDEX
    Explanations

    structural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    USART
    -0.09
     envy
    -0.08
    ativo
    -0.08
    ativamente
    -0.08
    /actions
    -0.08
    (iterator
    -0.08
     wasi
    -0.08
    Буд
    -0.08
     bitterness
    -0.08
    舔
    -0.08
    POSITIVE LOGITS
     ciment
    0.10
     mathem
    0.09
     расч
    0.09
     backbone
    0.08
     novel
    0.08
     mathematics
    0.08
     cálculo
    0.08
     gravitational
    0.08
     गण
    0.08
     Marvel
    0.08
    Act Density 0.023%

    No Known Activations