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

    Neuronpedia

    INDEX
    Explanations

    exclamations and definitive statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.51
     r
    0.43
            
    0.43
     qtd
    0.42
     ."
    0.42
    শেখ
    0.42
     wobei
    0.41
    ্ম
    0.41
     terdapat
    0.40
     .,
    0.39
    POSITIVE LOGITS
    !
    2.80
    ！
    2.50
    !)
    2.47
    !).
    2.36
    !”
    2.27
    !")
    2.27
    !),
    2.25
    !</
    2.25
    !]
    2.23
    !"
    2.20
    Act Density 0.085%

    No Known Activations