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

    Neuronpedia

    INDEX
    Explanations

    was, becomes, caused, is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    點
    0.40
    umbia
    0.39
     inadvertently
    0.38
     задума
    0.38
     increasingly
    0.38
     fãs
    0.38
     absolute
    0.37
     adicion
    0.36
    н
    0.36
    StartDate
    0.35
    POSITIVE LOGITS
    یدر
    0.45
     bubbling
    0.44
    廻
    0.42
    学生
    0.42
     tunnelling
    0.41
     regenv
    0.40
     licking
    0.40
    曛
    0.39
    gaxModule
    0.38
    𝙇
    0.38
    Act Density 0.000%

    No Known Activations