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

    Neuronpedia

    INDEX
    Explanations

    plural nouns ending in 'ers' or 'ors'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DI
    0.44
    Daniels
    0.41
    ستان
    0.40
       
    0.39
    atures
    0.39
    تباط
    0.39
     DHT
    0.38
    Prince
    0.38
     Witcher
    0.38
     امکان
    0.37
    POSITIVE LOGITS
    ponsored
    0.68
    hip
    0.67
    pace
    0.66
    hips
    0.63
    mith
    0.62
    upport
    0.61
    pecific
    0.60
    chaft
    0.56
    afety
    0.55
    leeve
    0.54
    Act Density 0.022%

    No Known Activations