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

    Neuronpedia

    INDEX
    Explanations

    question whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    稃
    0.50
     নেবে
    0.46
     Writer
    0.45
     চলবে
    0.42
     ቀላል
    0.42
     thisTrial
    0.41
    讨论
    0.40
    咿
    0.40
    简
    0.40
    手续
    0.40
    POSITIVE LOGITS
     doenças
    0.54
     karena
    0.48
     dringend
    0.48
     रोजाना
    0.47
     migraines
    0.47
     Bởi
    0.46
     serius
    0.46
     imbalances
    0.46
     banget
    0.45
     platelets
    0.44
    Act Density 0.001%

    No Known Activations