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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quella
    -0.07
    ictions
    -0.06
    ':''
    -0.06
     حک
    -0.06
     celui
    -0.06
    /_
    -0.06
    /rand
    -0.06
    ]<=
    -0.06
    �
    -0.06
    ีอ
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Amendments
    0.07
    mur
    0.07
    енти
    0.06
    าย
    0.06
    永久
    0.06
     Prospect
    0.06
     Slot
    0.06
    міністра
    0.06
    .cod
    0.06
    Act Density 0.001%

    No Known Activations