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

    Neuronpedia

    INDEX
    Explanations

    fraternity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ago
    -0.07
    pond
    -0.07
    DONE
    -0.07
    izzy
    -0.07
     Indicates
    -0.07
     Compar
    -0.07
     lĩnh
    -0.07
    lov
    -0.06
    aeda
    -0.06
     hone
    -0.06
    POSITIVE LOGITS
    爆出
    0.07
    -dropdown
    0.07
     kay
    0.07
    عائلة
    0.07
    בעל
    0.07
     Identity
    0.07
    贻
    0.06
     Ball
    0.06
    times
    0.06
    binary
    0.06
    Act Density 0.002%

    No Known Activations