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

    Neuronpedia

    INDEX
    Explanations

    explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulant
    -0.06
     Dependency
    -0.06
    intro
    -0.06
     PB
    -0.06
    inci
    -0.06
    tensor
    -0.06
     fascism
    -0.06
    ,)
    -0.06
    arry
    -0.06
     feedback
    -0.06
    POSITIVE LOGITS
     Codable
    0.07
     katıl
    0.06
    LOT
    0.06
     Events
    0.06
     upsetting
    0.06
    нять
    0.06
    lane
    0.06
     حالة
    0.06
    celed
    0.06
    \/\/
    0.06
    Act Density 0.000%

    No Known Activations