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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orado
    -0.07
     electoral
    -0.06
     trú
    -0.06
    605
    -0.06
    ENO
    -0.06
    611
    -0.06
     obstacles
    -0.06
    ocy
    -0.06
    μείο
    -0.06
     SE
    -0.06
    POSITIVE LOGITS
     writers
    0.10
     writer
    0.09
     Writers
    0.08
     Publishing
    0.07
     Writer
    0.07
    eated
    0.07
     withholding
    0.07
    dtype
    0.07
    ر
    0.07
     FileWriter
    0.07
    Act Density 0.019%

    No Known Activations