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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to respect, recognition, and commemoration

    oai_token-act-pair · gemini-2.0-flash

    honor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     honor
    -2.45
     honour
    -2.27
    honor
    -2.06
     Honor
    -2.05
     honors
    -2.00
     Honour
    -1.96
    Honor
    -1.94
     HONOR
    -1.88
    hon
    -1.70
     honours
    -1.70
    POSITIVE LOGITS
    исленность
    0.70
    GEBURTS
    0.66
     frets
    0.62
    WEBPACK
    0.59
    ftagPool
    0.59
     تكبرها
    0.59
     CreateTagHelper
    0.57
     MenuView
    0.56
     resourceCulture
    0.56
    MLLoader
    0.56
    Act Density 4.702%

    No Known Activations