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

    Neuronpedia

    INDEX
    Explanations

    breed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    虽
    -0.07
     face
    -0.07
     complex
    -0.06
    獨立
    -0.06
     amph
    -0.06
     Salv
    -0.06
     YT
    -0.06
    imag
    -0.06
     put
    -0.06
     chữ
    -0.06
    POSITIVE LOGITS
    芝
    0.07
     caffe
    0.07
    .writer
    0.07
     الصين
    0.07
    سقو
    0.07
    '");↵
    0.07
    .Writer
    0.07
     Pháp
    0.07
    <?>
    0.07
    Watcher
    0.07
    Act Density 0.064%

    No Known Activations