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

    Neuronpedia

    INDEX
    Explanations

    unexpected error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }
    1.94
    ]
    1.61
    -
    1.54
    يه
    1.53
     таки
    1.52
    (.*
    1.52
    "
    1.51
    )
    1.50
    (
    1.45
    ಿಣ
    1.41
    POSITIVE LOGITS
     Manuscripts
    1.70
     Kinetics
    1.66
    ра
    1.64
            
    1.63
     Executives
    1.62
     Explore
    1.61
     Whoever
    1.59
     auxquels
    1.59
     Meetings
    1.55
     Examine
    1.55
    Act Density 0.344%

    No Known Activations