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

    Neuronpedia

    INDEX
    Explanations

    hydrated, unhydrated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    qa
    0.74
    اقه
    0.72
    Purchase
    0.70
    Once
    0.66
    शा
    0.63
    Potion
    0.62
     அந்
    0.61
    Kath
    0.61
    ارة
    0.60
    Bromo
    0.59
    POSITIVE LOGITS
     rolls
    0.77
     clerk
    0.72
     Cunningham
    0.68
     clerks
    0.68
     campaigned
    0.68
     carpenter
    0.67
     carpenters
    0.67
     apparatus
    0.67
     employés
    0.67
    ximately
    0.66
    Act Density 0.000%

    No Known Activations