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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ert
    -0.07
     TJ
    -0.07
    68
    -0.07
     whe
    -0.07
     ts
    -0.06
    imiz
    -0.06
    Mocks
    -0.06
     kicking
    -0.06
    όν
    -0.06
     achievement
    -0.06
    POSITIVE LOGITS
     Canadiens
    0.07
     فرمود
    0.07
    .Le
    0.06
    expectException
    0.06
     Ala
    0.06
    (can
    0.06
    /write
    0.06
     ödem
    0.06
     BLE
    0.06
    _cond
    0.06
    Act Density 0.004%

    No Known Activations