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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sáng
    -0.06
     setVisible
    -0.06
     orgy
    -0.06
    _UART
    -0.06
    jeta
    -0.06
     rl
    -0.06
     BSP
    -0.06
     troubling
    -0.05
    )paren
    -0.05
     lạnh
    -0.05
    POSITIVE LOGITS
     exemption
    0.07
     atrocities
    0.07
    .Char
    0.07
    appearance
    0.07
     conditioned
    0.06
     compl
    0.06
    stub
    0.06
    ，都
    0.06
    ?,?,?,?,
    0.06
    ul
    0.06
    Act Density 0.001%

    No Known Activations