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

    Neuronpedia

    INDEX
    Explanations

    lobbying, favors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     favor
    -1.05
     favors
    -0.87
     regime
    -0.75
     favored
    -0.71
     favours
    -0.70
    regime
    -0.68
     favour
    -0.66
     favore
    -0.66
    fav
    -0.66
     Fav
    -0.65
    POSITIVE LOGITS
     disambiguazione
    0.83
     propOrder
    0.81
    theless
    0.79
     betweenstory
    0.75
     kaarangay
    0.68
    IntoConstraints
    0.65
    脚注の使い方
    0.64
    oa̍t
    0.62
    webElementXpaths
    0.61
     Baillargeon
    0.60
    Act Density 0.079%

    No Known Activations