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

    Neuronpedia

    INDEX
    Explanations

    passport validity or future extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ertid
    0.50
    idlo
    0.48
     χαρακτη
    0.48
    ERRORTYPE
    0.46
     bây
    0.46
    roj
    0.45
     marchandises
    0.45
    områ
    0.45
     ଆ
    0.44
     movimenti
    0.44
    POSITIVE LOGITS
    Soul
    0.57
    d
    0.52
    Progress
    0.51
    ோ
    0.50
     Pulitzer
    0.49
    Well
    0.48
     unresponsive
    0.48
    l
    0.48
     Main
    0.47
    ژ
    0.47
    Act Density 0.002%

    No Known Activations