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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lv
    -0.07
     stripslashes
    -0.07
    昇
    -0.07
     grav
    -0.07
    enario
    -0.07
     standpoint
    -0.06
    -sl
    -0.06
     κα
    -0.06
     Hide
    -0.06
    oe
    -0.06
    POSITIVE LOGITS
    has
    0.07
     Lis
    0.07
    ListGroup
    0.07
     İç
    0.06
     Daisy
    0.06
    lenmiş
    0.06
     ASAP
    0.06
    Krist
    0.06
    NSNotificationCenter
    0.06
    DetailsService
    0.06
    Act Density 0.003%

    No Known Activations