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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ืน
    -0.07
    áo
    -0.06
    $",
    -0.06
     mañana
    -0.06
    .dropdown
    -0.06
    rão
    -0.06
    ASE
    -0.06
    盾
    -0.06
    还需要
    -0.06
    eks
    -0.06
    POSITIVE LOGITS
     unpredictable
    0.07
    CU
    0.07
    pictures
    0.07
     interactive
    0.07
    ]\\
    0.06
    ]<
    0.06
    漱
    0.06
     Hung
    0.06
    -user
    0.06
     Lingu
    0.06
    Act Density 0.042%

    No Known Activations