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

    Neuronpedia

    INDEX
    Explanations

    ural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     butterfly
    -0.07
     Chew
    -0.07
     fly
    -0.07
    .flip
    -0.07
     ABS
    -0.06
    ack
    -0.06
     heroine
    -0.06
    itet
    -0.06
     Mom
    -0.06
    '-
    -0.06
    POSITIVE LOGITS
    OutOfRangeException
    0.06
     venta
    0.06
    一緒
    0.06
    Padding
    0.06
    rror
    0.06
     mentally
    0.06
    си
    0.06
     ハ
    0.06
    rome
    0.06
    ModelState
    0.06
    Act Density 0.001%

    No Known Activations