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

    Neuronpedia

    INDEX
    Explanations

    code delimiters or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cranberry
    0.31
    .
    0.28
     buckwheat
    0.28
    ,
    0.27
     callus
    0.26
    .。
    0.26
    富
    0.26
     পালন
    0.25
    বাড়
    0.25
     অ
    0.24
    POSITIVE LOGITS
     yine
    0.36
     zweite
    0.35
    şey
    0.34
     tenuous
    0.34
     demonic
    0.33
    ۲۰
    0.33
    esist
    0.33
     viciss
    0.32
    මෙ
    0.32
     भी
    0.32
    Act Density 0.206%

    No Known Activations