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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oran
    -0.07
     bush
    -0.06
     прод
    -0.06
    ení
    -0.06
    leep
    -0.06
    ining
    -0.06
     design
    -0.06
    ICT
    -0.06
    gow
    -0.06
    jump
    -0.06
    POSITIVE LOGITS
     seventh
    0.07
    _AL
    0.07
     rozdíl
    0.07
     siguiente
    0.06
     tercer
    0.06
    [Double
    0.06
     будущ
    0.06
    .swap
    0.06
    -нибудь
    0.06
    联系
    0.06
    Act Density 0.012%

    No Known Activations