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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ."},
    1.94
    ."],
    1.85
    ."',
    1.80
     }}$,
    1.79
    }\}$.
    1.67
    }]$,
    1.66
    }}$,
    1.63
    ."),
    1.62
     }}$.
    1.62
    ")).
    1.60
    POSITIVE LOGITS
    )
    3.19
    ）
    2.50
    ")
    2.37
    ')
    2.35
    ())
    2.28
    ’)
    2.23
     )
    2.18
    ]
    2.15
    ”)
    2.12
    _)
    2.09
    Act Density 2.224%

    No Known Activations