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

    Neuronpedia

    INDEX
    Explanations

    sql distinct counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Humphries
    0.41
     earned
    0.40
     الحركة
    0.40
     weighted
    0.38
     compteur
    0.38
     komis
    0.38
    計測
    0.38
     endure
    0.37
     idios
    0.37
     Komis
    0.37
    POSITIVE LOGITS
    FName
    0.39
    requestId
    0.38
    ราม
    0.38
    routeName
    0.37
    paper
    0.37
     requests
    0.37
    RequestId
    0.37
    าราง
    0.36
    慌
    0.36
    학년
    0.36
    Act Density 0.000%

    No Known Activations