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

    Neuronpedia

    INDEX
    Explanations

    Wendy's McDonald's Parkinson's Christie's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ylan
    0.41
    氇
    0.39
     Classic
    0.37
     Buren
    0.37
    த்ரே
    0.37
     tolerated
    0.37
    nati
    0.37
    argo
    0.36
     Mats
    0.36
     gadgets
    0.36
    POSITIVE LOGITS
    ๆ
    0.50
    وں
    0.44
    們
    0.42
    ंस
    0.42
    נים
    0.41
    ^{*}$,
    0.40
    さんも
    0.40
     ๆ
    0.39
    斯的
    0.39
    များနှင့်
    0.39
    Act Density 0.007%

    No Known Activations