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

    Neuronpedia

    INDEX
    Explanations

    Random text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Generates
    -0.06
     exemple
    -0.06
    -0.06
    rious
    -0.06
     disposing
    -0.06
    .SelectedItem
    -0.06
    .bed
    -0.06
    SourceType
    -0.06
     readable
    -0.06
    :right
    -0.06
    POSITIVE LOGITS
    ивать
    0.07
    يلاد
    0.07
    lz
    0.06
    证明
    0.06
     мот
    0.06
    .setParameter
    0.06
     стало
    0.06
     lessen
    0.06
     рас
    0.06
     expend
    0.06
    Act Density 0.005%

    No Known Activations