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

    Neuronpedia

    INDEX
    Explanations

    go

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pat
    -0.07
     Apprent
    -0.07
     apprentices
    -0.07
     dette
    -0.07
     differences
    -0.07
     Warn
    -0.06
    better
    -0.06
     goals
    -0.06
     hippoc
    -0.06
     wildlife
    -0.06
    POSITIVE LOGITS
     Chrome
    0.08
    𦰡
    0.07
     Báo
    0.06
    潮
    0.06
    有几个
    0.06
    =wx
    0.06
    ope
    0.06
    /question
    0.06
    ∠
    0.06
    	cache
    0.06
    Act Density 0.007%

    No Known Activations