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

    Neuronpedia

    INDEX
    Explanations

    M

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ephy
    -0.07
    xab
    -0.07
     Blonde
    -0.07
    ohana
    -0.07
    xbe
    -0.07
    Telegram
    -0.07
     پژ
    -0.07
    estre
    -0.07
     unbe
    -0.07
    .Bunifu
    -0.07
    POSITIVE LOGITS
     D
    0.14
     S
    0.13
     F
    0.12
     H
    0.12
     M
    0.12
     T
    0.12
     G
    0.12
     C
    0.11
     B
    0.11
     K
    0.11
    Act Density 1.340%

    No Known Activations