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

    Neuronpedia

    INDEX
    Explanations

    performance tracking and analytics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.13
    os
    1.02
    ne
    1.02
    ER
    0.97
    在
    0.93
    AT
    0.92
    С
    0.91
    О
    0.89
    ILL
    0.88
    ON
    0.87
    POSITIVE LOGITS
    지
    1.05
    ach
    1.01
    าย
    0.92
    ↵
    0.91
    ט
    0.86
    ant
    0.84
    та
    0.80
    ד
    0.80
     성능
    0.80
    ле
    0.79
    Act Density 0.051%

    No Known Activations