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

    Neuronpedia

    INDEX
    Explanations

    code blocks and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etés
    0.39
     pate
    0.38
     punctual
    0.38
     दुसरे
    0.38
    âh
    0.37
    এছ
    0.36
     omnichannel
    0.36
     excer
    0.36
    ورية
    0.36
    CharSequence
    0.36
    POSITIVE LOGITS
    0.46
    ಬೇಕ
    0.39
    ட்சிய
    0.38
    !"
    0.36
    目標
    0.36
    drawImage
    0.35
    0.35
     takım
    0.35
    0.35
     !!!
    0.35
    Act Density 0.005%

    No Known Activations