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

    Neuronpedia

    INDEX
    Explanations

    spending time and effort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chodzi
    0.81
    interference
    0.78
     मिलना
    0.74
     Neighbor
    0.71
    Ờ
    0.71
     разными
    0.70
     устройств
    0.68
    Fast
    0.68
    বাহী
    0.67
     systemu
    0.67
    POSITIVE LOGITS
     precious
    1.30
     evenings
    1.23
     afternoons
    1.21
     effort
    1.17
     hours
    1.15
     considerable
    1.15
     nights
    1.12
     weekends
    1.08
     exorbitant
    1.08
     sleepless
    1.06
    Act Density 0.052%

    No Known Activations