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

    Neuronpedia

    INDEX
    Explanations

    (v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PREVIEW
    -0.07
     Civ
    -0.07
     findet
    -0.07
     Reuters
    -0.06
     authenticity
    -0.06
     kol
    -0.06
    Widget
    -0.06
    _Metadata
    -0.06
     CP
    -0.06
     Regions
    -0.06
    POSITIVE LOGITS
    روج
    0.06
    _lambda
    0.06
    ξι
    0.06
     Deutschland
    0.06
    нт
    0.06
    CLEAR
    0.06
    寶
    0.06
    ettings
    0.06
    ับการ
    0.06
     millones
    0.05
    Act Density 0.000%

    No Known Activations