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

    Neuronpedia

    INDEX
    Explanations

    tables and code separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    обс
    0.89
     сравнению
    0.87
    wilderness
    0.87
    enya
    0.86
    ⓞ
    0.86
    __:
    0.85
     Subsec
    0.85
    getParent
    0.84
    닼
    0.84
    navigationItem
    0.84
    POSITIVE LOGITS
    ↵
    0.95
     \\
    0.79
     fres
    0.77
    \
    0.76
     *
    0.74
    <0x0D>
    0.72
    ches
    0.68
    「
    0.64
     прикла
    0.64
     aster
    0.64
    Act Density 0.058%

    No Known Activations