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

    Neuronpedia

    INDEX
    Explanations

    attached to email

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    2.62
    ه
    2.43
    ι
    2.37
    ்
    2.20
    ל
    2.17
    $_
    2.13
    ுங்கள்
    2.12
    ра
    2.07
    هي
    2.03
    oje
    2.01
    POSITIVE LOGITS
     hereto
    2.85
    னர்
    2.70
    に
    2.54
    로
    2.51
    nogo
    2.28
    驥
    2.26
    𝙇
    2.25
    razine
    2.25
     beban
    2.22
    assment
    2.21
    Act Density 0.006%

    No Known Activations