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

    Neuronpedia

    INDEX
    Explanations

    duration of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jovi
    0.28
     everytime
    0.26
     sneaky
    0.26
     yaşanan
    0.26
     മനസ
    0.26
     Paddington
    0.26
    hashtag
    0.26
    Truthy
    0.25
     @_
    0.25
     Selfie
    0.25
    POSITIVE LOGITS
    American
    0.28
     chiefly
    0.26
     American
    0.25
    а
    0.25
    Д
    0.24
     apparent
    0.24
    like
    0.24
    エ
    0.24
    О
    0.23
     reorganization
    0.23
    Act Density 0.005%

    No Known Activations