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

    Neuronpedia

    INDEX
    Explanations

    griffin, cipher, elixir, sentinel, alert

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    1.73
    t
    1.36
    in
    1.20
    ية
    1.09
    tedir
    1.09
    et
    1.06
    siniz
    1.01
    at
    0.98
    é
    0.91
    id
    0.89
    POSITIVE LOGITS
     נק
    1.06
    ur
    1.05
     צ
    1.02
     નંબર
    1.01
     کر
    1.00
     که
    0.99
     وی
    0.98
     የተለያዩ
    0.97
     ನಿಮ್ಮ
    0.96
     ከፍተኛ
    0.96
    Act Density 0.008%

    No Known Activations