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

    Neuronpedia

    INDEX
    Explanations

    ability and performance contrasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    」、「
    0.48
     saloon
    0.46
     pierwsze
    0.44
     Sous
    0.42
     Stal
    0.42
     Cessna
    0.41
     dá
    0.41
     d
    0.40
     Kei
    0.40
     Stove
    0.40
    POSITIVE LOGITS
    ્ઞ
    0.46
    铉
    0.46
    Healthcare
    0.44
    词
    0.42
     brownish
    0.42
    ריך
    0.41
    NHS
    0.41
    ός
    0.41
    崩溃
    0.40
    知识
    0.40
    Act Density 0.006%

    No Known Activations