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

    Neuronpedia

    INDEX
    Explanations

    Placeholder/nonsense text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ─
    -0.06
    zelf
    -0.06
    PosX
    -0.06
    azı
    -0.06
    ynchronous
    -0.06
     �
    -0.06
    DownLatch
    -0.06
    ẩm
    -0.06
    _TOTAL
    -0.06
    ρει
    -0.06
    POSITIVE LOGITS
     respiratory
    0.07
     Chairs
    0.07
    LES
    0.07
     innings
    0.07
     carries
    0.07
     cook
    0.06
    .keyboard
    0.06
     generators
    0.06
     sighed
    0.06
     book
    0.06
    Act Density 0.029%

    No Known Activations