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

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hike
    -0.07
    .tree
    -0.07
    -0.07
    ]),
    -0.07
     ],
    -0.07
    ],
    -0.07
    ),
    -0.07
    .cancel
    -0.07
     }):
    -0.07
    )
    -0.07
    POSITIVE LOGITS
     --↵
    0.08
     *↵
    0.08
    --↵
    0.08
    !↵
    0.08
     ś
    0.07
     -↵
    0.07
     příležit
    0.07
    *↵
    0.07
     —↵
    0.07
    áct
    0.07
    Act Density 0.197%

    No Known Activations