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

    Neuronpedia

    INDEX
    Explanations

    years in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ormai
    1.51
     dentre
    1.40
     તથા
    1.36
     sekaligus
    1.36
     ʻ
    1.35
     yalnız
    1.30
     sämt
    1.28
     irmãos
    1.27
     fazia
    1.26
     khususnya
    1.25
    POSITIVE LOGITS
    ="))
    1.65
    })
    1.60
    ))
    1.50
     }=
    1.48
    )=
    1.44
    _)
    1.43
    )).
    1.36
    }=
    1.33
    anceled
    1.33
    ehicle
    1.32
    Act Density 0.502%

    No Known Activations