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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ALLOC
    -0.07
     advanced
    -0.07
    年上半年
    -0.07
    是我国
    -0.07
    OutOfBoundsException
    -0.07
    혼
    -0.07
     OVER
    -0.07
     mừng
    -0.07
    SetActive
    -0.07
    multiple
    -0.07
    POSITIVE LOGITS
    .Body
    0.07
    LATED
    0.07
     displayed
    0.07
     slid
    0.07
     Julia
    0.07
     knit
    0.07
    (robot
    0.06
    嵋
    0.06
     robot
    0.06
     haired
    0.06
    Act Density 0.134%

    No Known Activations