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

    Neuronpedia

    INDEX
    Explanations

    introduces explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elseif
    0.69
    ibi
    0.69
     Ib
    0.67
     শব্দটি
    0.67
     prep
    0.66
    予以
    0.65
    ப்பே
    0.64
     ib
    0.64
     არა
    0.63
     образование
    0.62
    POSITIVE LOGITS
    écies
    0.72
    𝐣
    0.70
    μφωνα
    0.69
    ஜ
    0.68
    roph
    0.68
    nics
    0.68
    Ꭻ
    0.67
    olid
    0.67
    خذ
    0.67
     เคย
    0.65
    Act Density 0.014%

    No Known Activations