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

    Neuronpedia

    INDEX
    Explanations

    molecules and molecular discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ما
    1.27
    ра
    1.05
    ك
    0.98
    را
    0.94
    ۸
    0.92
    ма
    0.90
    ш
    0.90
    𝙙
    0.89
    ۲
    0.83
    כ
    0.82
    POSITIVE LOGITS
     Molecule
    0.95
     Molecules
    0.93
    ero
    0.91
    us
    0.88
     molecules
    0.86
     molecule
    0.85
    ↵
    0.84
    g
    0.83
     molecular
    0.82
     by
    0.81
    Act Density 0.006%

    No Known Activations