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

    Neuronpedia

    INDEX
    Explanations

    numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lichkeit
    0.38
    Detection
    0.38
     admissibility
    0.37
     imposition
    0.34
     airspace
    0.34
     detection
    0.33
    лювання
    0.33
     inhomogeneity
    0.33
    ریت
    0.33
     expulsion
    0.32
    POSITIVE LOGITS
     billion
    0.53
     개의
    0.53
     বছর
    0.50
    개의
    0.49
     million
    0.49
    9
    0.49
     octobre
    0.48
     marzo
    0.48
     décembre
    0.47
     años
    0.47
    Act Density 0.018%

    No Known Activations