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

    Neuronpedia

    INDEX
    Explanations

    German and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h4>
    0.75
    /}
    0.72
    ,}
    0.72
    </h3>
    0.70
     Traf
    0.67
     Da
    0.66
    '}
    0.66
     होते
    0.65
    !}
    0.65
    পাই
    0.64
    POSITIVE LOGITS
     paintings
    1.29
    黉
    1.28
     pinnacle
    1.14
     Paintings
    1.10
     lifestyles
    1.08
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.00
     reminisc
    0.99
    怙
    0.98
    ↵↵↵↵↵↵↵↵↵↵
    0.97
     felony
    0.96
    Act Density 0.008%

    No Known Activations