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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .apply
    -0.06
    *))
    -0.06
    .newBuilder
    -0.06
     сход
    -0.06
     SAVE
    -0.06
     ugl
    -0.06
    expects
    -0.06
     nw
    -0.06
     newcomers
    -0.06
     있어서
    -0.06
    POSITIVE LOGITS
     Gins
    0.07
     Bộ
    0.07
     Sys
    0.07
    iae
    0.07
    льт
    0.07
    atching
    0.07
    ERM
    0.07
    اهش
    0.07
    IGATION
    0.06
    ERNEL
    0.06
    Act Density 0.024%

    No Known Activations