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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _));↵
    -0.07
    >());↵
    -0.07
    "},"
    -0.07
    (pad
    -0.06
    ｗｗ
    -0.06
     ara
    -0.06
    ]);
    -0.06
     determines
    -0.06
    uelle
    -0.06
    }});↵
    -0.06
    POSITIVE LOGITS
     Future
    0.07
    MISSION
    0.07
    ainer
    0.07
     (**
    0.06
    ποι
    0.06
     Flesh
    0.06
    connect
    0.06
    manda
    0.06
    动
    0.06
    ITED
    0.06
    Act Density 0.000%

    No Known Activations