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

    Neuronpedia

    INDEX
    Explanations

    signal phrase, molecules, Diamond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .?
    0.50
    ,?
    0.48
    ió
    0.48
    gaxModule
    0.46
    })}{\
    0.45
     denomin
    0.45
     Kyrgyzstan
    0.43
    нили
    0.43
     січня
    0.43
    izos
    0.43
    POSITIVE LOGITS
    Olá
    0.59
     núcle
    0.57
    from
    0.55
     factorization
    0.52
    Hej
    0.52
    ﺿ
    0.52
    안녕하세요
    0.52
    ﺑ
    0.51
    ﺛ
    0.50
    ঙে
    0.49
    Act Density 0.000%

    No Known Activations