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

    Neuronpedia

    INDEX
    Explanations

    modeling complex dynamic systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.97
    ların
    0.97
    ları
    0.92
    larına
    0.87
    um
    0.84
    érez
    0.83
    larıyla
    0.82
    ară
    0.82
     élargies
    0.82
    وں
    0.81
    POSITIVE LOGITS
    ;
    1.39
     Modeling
    1.16
    Modeling
    1.11
    }
    1.05
    </b>
    1.03
    建模
    1.01
    },
    0.98
     modeling
    0.97
    '
    0.95
     Modelling
    0.95
    Act Density 0.016%

    No Known Activations