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

    Neuronpedia

    INDEX
    Explanations

    establishing relationships between words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SalesReport
    0.41
    ailand
    0.41
     oftentimes
    0.40
     ours
    0.39
     نیست
    0.38
    Aren
    0.38
    Unknown
    0.38
     देयर
    0.37
     سرحد
    0.37
    ”
    0.37
    POSITIVE LOGITS
     remained
    0.49
     became
    0.47
     augmenting
    0.45
     insofar
    0.44
     fortunate
    0.43
     zuerst
    0.42
    負責
    0.42
     zunächst
    0.42
     undertook
    0.42
     straightforward
    0.41
    Act Density 0.004%

    No Known Activations