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

    Neuronpedia

    INDEX
    Explanations

    corrupt, corcyran, corfu, coroutines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ement
    0.76
    मान
    0.74
    elmi
    0.73
    ීම්
    0.73
    schw
    0.73
    Visiting
    0.72
    フォ
    0.72
    erve
    0.71
    armes
    0.70
     Aufenthalt
    0.70
    POSITIVE LOGITS
    rugated
    1.28
    coran
    1.22
    outines
    1.18
     Cor
    1.13
    onavirus
    1.12
    Cor
    1.09
     COR
    1.08
    outine
    1.07
    onavir
    1.04
    cor
    1.04
    Act Density 0.047%

    No Known Activations