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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -map
    -0.08
     task
    -0.08
     rejected
    -0.07
    128
    -0.07
    _tl
    -0.07
    -prefix
    -0.07
    订
    -0.07
    通信
    -0.07
    _past
    -0.07
    ActionResult
    -0.06
    POSITIVE LOGITS
    .Setup
    0.07
     setCurrent
    0.06
    ってる
    0.06
    ượng
    0.06
    inely
    0.06
    umed
    0.06
    porate
    0.06
    ContentPane
    0.06
     portray
    0.06
     knowingly
    0.06
    Act Density 0.006%

    No Known Activations