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

    Neuronpedia

    INDEX
    Explanations

    hands-on learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hand
    0.45
     পাট
    0.43
    Hand
    0.43
     hand
    0.42
     infra
    0.39
    Handler
    0.38
     Routine
    0.38
     Hanover
    0.38
     authentication
    0.37
     Clim
    0.37
    POSITIVE LOGITS
     práct
    0.43
    的一种
    0.41
    耳朵
    0.40
    ệu
    0.39
    deep
    0.39
     hiyo
    0.39
    elabel
    0.38
    ,\,
    0.38
    ლის
    0.38
     praktische
    0.38
    Act Density 0.003%

    No Known Activations