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

    Neuronpedia

    INDEX
    Explanations

    easy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     easy
    -2.70
    easy
    -2.31
     easier
    -2.16
     Easy
    -2.02
    Easy
    -1.96
     EASY
    -1.76
     easiest
    -1.75
    easier
    -1.74
     fácil
    -1.68
     easily
    -1.60
    POSITIVE LOGITS
     فريبيس
    0.61
    going
    0.61
     to
    0.60
    rungsseite
    0.60
    StreetMap
    0.56
    ègre
    0.55
     désolés
    0.54
    enggarakan
    0.54
    AddTagHelper
    0.54
    WriteTagHelper
    0.54
    Act Density 0.035%

    No Known Activations