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

    Neuronpedia

    INDEX
    Explanations

    personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cặp
    -0.07
     каждом
    -0.07
    din
    -0.07
     characteristic
    -0.07
     projection
    -0.07
     pessoas
    -0.06
    局部
    -0.06
    员
    -0.06
     GF
    -0.06
    如果是
    -0.06
    POSITIVE LOGITS
    Binder
    0.08
     binary
    0.07
    UNDLE
    0.07
    irty
    0.07
     Byz
    0.07
    _twitter
    0.07
    ERNEL
    0.07
     thất
    0.07
    _barrier
    0.07
    緩
    0.06
    Act Density 0.126%

    No Known Activations