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

    Neuronpedia

    INDEX
    Explanations

    device modes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ʻ
    0.35
     stockbild
    0.33
     ການ
    0.32
    fi
    0.32
    जू
    0.31
    Ī
    0.30
    मताओं
    0.30
     নিয়ন্ত্রণে
    0.30
    ಮೆ
    0.30
    рім
    0.29
    POSITIVE LOGITS
    ↵
    1.02
    ↵↵
    0.94
    ↵↵↵↵
    0.91
    ↵↵↵↵↵
    0.86
    ↵↵↵
    0.85
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.79
    ↵↵↵↵↵↵
    0.75
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.74
    ↵↵↵↵↵↵↵↵
    0.73
    ↵↵↵↵↵↵↵
    0.73
    Act Density 2.690%

    No Known Activations