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

    Neuronpedia

    INDEX
    Explanations

    perception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     démocr
    -0.64
     dieux
    -0.64
     scolaires
    -0.64
     économies
    -0.60
     Grecs
    -0.60
     générations
    -0.58
     paysages
    -0.58
     enfans
    -0.57
     réguli
    -0.57
     affari
    -0.56
    POSITIVE LOGITS
    >--}}
    0.53
    loroethene
    0.52
    odeficiency
    0.52
     كمان
    0.51
    ToProps
    0.49
     betweenstory
    0.49
    bria
    0.48
    polski
    0.48
    ometal
    0.47
    CppMethod
    0.47
    Act Density 0.092%

    No Known Activations