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

    Neuronpedia

    INDEX
    Explanations

    past tense, scanner, beliefs, address, owner, macOS, year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    до
    1.03
     समर्
    0.84
    ди
    0.84
    நபியே
    0.77
     stesse
    0.77
    धर्म
    0.76
     quarries
    0.76
     WHICH
    0.75
    ༅
    0.75
     vaksin
    0.74
    POSITIVE LOGITS
    /
    0.92
    mer
    0.88
    ation
    0.84
    ty
    0.84
    ger
    0.83
    il
    0.83
    ment
    0.82
    ost
    0.80
    '
    0.80
    om
    0.79
    Act Density 0.001%

    No Known Activations