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

    Neuronpedia

    INDEX
    Explanations

    people's roles followed by 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    っと
    0.38
     *)
    0.36
    中の
    0.34
     ],
    0.33
     
    0.33
    …).
    0.33
     ειδ
    0.33
     decembrie
    0.33
    മായ
    0.33
     önem
    0.33
    POSITIVE LOGITS
    ’
    0.87
    '/
    0.81
    ’-
    0.79
    '-
    0.78
    '_
    0.74
    '
    0.72
    '">
    0.67
    \'
    0.64
    ̕
    0.63
    ´
    0.63
    Act Density 0.021%

    No Known Activations