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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     non
    -0.07
     Non
    -0.07
    .percent
    -0.07
     Als
    -0.07
    𝘦
    -0.07
    已经成为
    -0.07
    /")
    -0.06
     Strange
    -0.06
    唏
    -0.06
    '=>$_
    -0.06
    POSITIVE LOGITS
    ImageButton
    0.07
    ייע
    0.07
    芼
    0.07
     compassion
    0.07
     toolbox
    0.07
    (service
    0.07
     zobowią
    0.07
    viewModel
    0.07
    꿘
    0.07
     yayınlan
    0.07
    Act Density 0.028%

    No Known Activations