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

    Neuronpedia

    INDEX
    Explanations

    born

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Set
    -0.07
    Met
    -0.07
    Stay
    -0.06
     센
    -0.06
     Whereas
    -0.06
    .Inf
    -0.06
     pleasures
    -0.06
     wor
    -0.06
     cycles
    -0.06
    Shapes
    -0.06
    POSITIVE LOGITS
    ...",↵
    0.07
    prise
    0.06
    isman
    0.06
    ');↵
    0.06
     ```↵
    0.06
     домов
    0.06
     $↵↵
    0.06
    uso
    0.06
    ...',↵
    0.06
    σεις
    0.06
    Act Density 0.002%

    No Known Activations