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

    Neuronpedia

    INDEX
    Explanations

    logical relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alley
    -0.07
    acades
    -0.07
     Kund
    -0.07
     подраз
    -0.06
    .accel
    -0.06
     Quincy
    -0.06
     Hasan
    -0.06
     perseverance
    -0.06
    ..
    -0.06
     포함
    -0.06
    POSITIVE LOGITS
    ddd
    0.07
     nisi
    0.07
     toh
    0.06
     Hispanic
    0.06
    cmpeq
    0.06
     violated
    0.06
    (BitConverter
    0.06
    uento
    0.06
    **
↵
    0.06
    Loaded
    0.06
    Act Density 0.023%

    No Known Activations