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

    Neuronpedia

    INDEX
    Explanations

    race, guidance, Hello

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.06
    thed
    1.03
     various
    1.00
     관련된
    0.99
    ____
    0.98
    ंगिक
    0.98
    teenth
    0.97
    ლის
    0.96
     any
    0.96
     distaste
    0.96
    POSITIVE LOGITS
     llamada
    1.10
     pusieron
    1.04
     geen
    1.00
     chiamato
    0.98
     chiamata
    0.95
     llamado
    0.94
    ගෙන
    0.94
     построен
    0.92
     divor
    0.92
     derecha
    0.92
    Act Density 0.001%

    No Known Activations