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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     receiver
    -0.07
    .d
    -0.07
     overlook
    -0.07
     challenged
    -0.07
     hat
    -0.07
     girlfriends
    -0.07
     lament
    -0.06
    uclear
    -0.06
    831
    -0.06
     Samp
    -0.06
    POSITIVE LOGITS
    EXPR
    0.07
    λη
    0.06
    utedString
    0.06
     StreamLazy
    0.06
    *******↵
    0.06
     реб
    0.06
     grips
    0.06
     frm
    0.06
    _INCLUDE
    0.06
     MainPage
    0.06
    Act Density 0.048%

    No Known Activations