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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     effectiveness
    -0.06
    界
    -0.06
    '.↵
    -0.06
     (↵
    -0.06
    419
    -0.06
    iting
    -0.06
    ull
    -0.06
    ?"↵
    -0.05
     acknowledgment
    -0.05
    '↵
    -0.05
    POSITIVE LOGITS
    "))
    0.07
    ']],
    0.07
    ]\
    0.07
    }')
    0.07
    )
    0.07
    ')
    0.07
    ]))
    0.07
    ])]
    0.07
    ")}
    0.07
    '])
    0.07
    Act Density 0.088%

    No Known Activations