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

    Neuronpedia

    INDEX
    Explanations

    feelings and states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    é
    0.83
    ри
    0.73
    ك
    0.71
    е
    0.70
    0.69
     стоимо
    0.69
    ру
    0.68
     apartamentos
    0.68
     Earrings
    0.68
     Reminder
    0.67
    POSITIVE LOGITS
    ि
    0.87
    ្នក
    0.79
    ÇÕES
    0.79
    नाल्ड
    0.76
    洸
    0.71
    neze
    0.71
     وحتى
    0.68
    讶
    0.68
    toadd
    0.67
    ngthen
    0.66
    Act Density 0.015%

    No Known Activations