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

    Neuronpedia

    INDEX
    Explanations

    TL;DR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.71
    )
    0.63
     B
    0.62
     R
    0.58
     K
    0.57
     U
    0.57
    Won
    0.57
    는
    0.57
    ู
    0.57
    ט
    0.57
    POSITIVE LOGITS
    gène
    0.66
     препарат
    0.65
     универса
    0.61
     میں
    0.61
    ﺕ
    0.59
     об
    0.58
     ин
    0.58
    溂
    0.58
     αντι
    0.58
     anisot
    0.57
    Act Density 0.000%

    No Known Activations