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

    Neuronpedia

    INDEX
    Explanations

    working with specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lobo
    0.88
    คล
    0.85
     laps
    0.85
     NIR
    0.79
     Dodger
    0.78
    犾
    0.77
     brain
    0.76
     റി
    0.75
     ইসলামাবাদ
    0.75
     Ilana
    0.75
    POSITIVE LOGITS
     ছাড়াও
    0.82
    cities
    0.76
     edifício
    0.73
     Cert
    0.71
    ‌.
    0.71
    ec
    0.71
     Appointments
    0.70
    naked
    0.70
     Sizes
    0.70
     Sache
    0.69
    Act Density 0.001%

    No Known Activations