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

    Neuronpedia

    INDEX
    Explanations

    can and cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     został
    0.28
     metabolized
    0.28
     रूप
    0.28
    owanym
    0.27
     повністю
    0.27
    被
    0.26
     لأنه
    0.26
    完全に
    0.26
     دروس
    0.26
     मार्केट
    0.26
    POSITIVE LOGITS
    dims
    0.29
    ্ড
    0.28
     Fortune
    0.28
     Farm
    0.27
     Cinderella
    0.27
    耧
    0.27
     outstretched
    0.27
     ull
    0.27
     wreaths
    0.26
     Clipboard
    0.26
    Act Density 0.004%

    No Known Activations