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

    Neuronpedia

    INDEX
    Explanations

    estate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()=>{
    1.23
    ↵↵
    1.17
    ↵
    1.08
    ня
    1.08
    тся
    1.08
    くらい
    1.08
    어야
    1.08
    ized
    1.06
    つの
    1.04
    க்கொண்ட
    1.04
    POSITIVE LOGITS
     również
    1.25
    ط
    1.23
     erfolgte
    1.20
    এবং
    1.18
    ifiably
    1.18
    លើ
    1.16
    kend
    1.16
     railings
    1.16
    ים
    1.14
    7
    1.13
    Act Density 0.002%

    No Known Activations