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

    Neuronpedia

    INDEX
    Explanations

    stolen data, credentials, search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EMF
    0.44
    梘
    0.40
     pausa
    0.37
     geï
    0.37
    insertAdjacent
    0.37
     ක්ර
    0.36
    izie
    0.36
     نک
    0.35
     sited
    0.35
    Strategy
    0.35
    POSITIVE LOGITS
    setScene
    0.42
     werk
    0.42
     filmm
    0.42
    sqcup
    0.42
    votes
    0.41
     notValid
    0.40
     ތ
    0.40
    éricas
    0.39
    torio
    0.39
    ऊस
    0.39
    Act Density 0.002%

    No Known Activations