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

    Neuronpedia

    INDEX
    Explanations

    laws of acceleration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Preschool
    0.49
     preschool
    0.46
     Nursery
    0.43
     elicit
    0.42
     observers
    0.42
     Kindergarten
    0.42
     preschoolers
    0.41
     mimic
    0.39
     kanilang
    0.39
     njih
    0.39
    POSITIVE LOGITS
     provincias
    0.39
    សា
    0.39
     ৷
    0.38
     فلس
    0.38
    ﹐
    0.37
    ొప్పి
    0.37
     '+':
    0.37
    ๅ
    0.36
    slidesPer
    0.36
    贱
    0.36
    Act Density 0.001%

    No Known Activations