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

    Neuronpedia

    INDEX
    Explanations

    names and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foal
    0.46
     empresa
    0.46
     அதிசயம்
    0.45
     pliers
    0.44
     Drums
    0.44
     it
    0.42
     الماء
    0.42
     idiots
    0.42
     ramo
    0.42
     مقدار
    0.42
    POSITIVE LOGITS
     who
    0.43
     व्यक्तित्व
    0.42
    haben
    0.41
    ^{
    0.39
    uste
    0.39
    bounded
    0.39
    took
    0.39
     quien
    0.39
    ның
    0.39
    의
    0.38
    Act Density 0.007%

    No Known Activations