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

    Neuronpedia

    INDEX
    Explanations

    such as examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anything
    0.84
     largely
    0.83
     hugely
    0.80
     disrupted
    0.79
     vastly
    0.79
     messed
    0.77
     shockingly
    0.77
     sidelined
    0.76
     overwhelmingly
    0.73
     ruined
    0.73
    POSITIVE LOGITS
    或
    0.83
    および
    0.80
    或者
    0.80
     그리고
    0.80
     или
    0.78
    Favorite
    0.75
     或
    0.74
     وال
    0.74
    ecuzione
    0.73
    而非
    0.73
    Act Density 0.038%

    No Known Activations