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

    Neuronpedia

    INDEX
    Explanations

    macro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CAMERA
    -0.08
    italize
    -0.07
    _FIX
    -0.07
    ບ
    -0.07
    .members
    -0.07
     evaluator
    -0.07
    .factor
    -0.07
     seriousness
    -0.06
    (_,
    -0.06
     актуальн
    -0.06
    POSITIVE LOGITS
     Reef
    0.07
    _assert
    0.07
    发行
    0.07
    _MISS
    0.06
    订单
    0.06
    残疾
    0.06
    弃
    0.06
    景点
    0.06
    씯
    0.06
     tools
    0.06
    Act Density 0.401%

    No Known Activations