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

    Neuronpedia

    INDEX
    Explanations

    something/someone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.71
     незавершена
    -0.68
    StreetMap
    -0.66
     للمعارف
    -0.65
    ⓧ
    -0.65
     Wicidata
    -0.63
     ddelweddau
    -0.63
    󠁿
    -0.61
    Tembelea
    -0.60
    quels
    -0.60
    POSITIVE LOGITS
     as
    0.65
     andata
    0.56
     réessayer
    0.54
     pouvait
    0.53
     abgeschlossen
    0.50
     poteva
    0.50
     pouvant
    0.50
     propOrder
    0.48
     comprenant
    0.48
     could
    0.48
    Act Density 0.001%

    No Known Activations