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

    Neuronpedia

    INDEX
    Explanations

    years, dates, and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Biography
    0.45
     posthum
    0.45
     December
    0.45
     Harus
    0.45
     Equals
    0.43
    ivariate
    0.43
     नाबाल
    0.42
    つまり
    0.42
    ൬
    0.42
     Finances
    0.42
    POSITIVE LOGITS
    Knife
    0.42
     carrot
    0.40
     нож
    0.40
    height
    0.39
     cream
    0.39
    ρά
    0.39
     γά
    0.39
    πό
    0.38
     dome
    0.38
     poros
    0.38
    Act Density 0.001%

    No Known Activations