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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Factor
    -0.07
    ])**
    -0.06
     migliori
    -0.06
    Lib
    -0.06
     ceased
    -0.06
    нь
    -0.06
    Sr
    -0.06
     JR
    -0.06
    탈
    -0.06
    )L
    -0.06
    POSITIVE LOGITS
    때
    0.06
     土
    0.06
    obra
    0.06
    addItem
    0.06
    ै?↵
    0.06
    ….↵↵
    0.06
    átek
    0.06
    issenschaft
    0.06
    LOOD
    0.06
    utut
    0.06
    Act Density 0.003%

    No Known Activations