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

    Neuronpedia

    INDEX
    Explanations

    deploy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    旃
    0.39
     mantenimiento
    0.38
     Fatigue
    0.38
     ضبط
    0.37
     для
    0.36
     também
    0.36
     （
    0.36
    สำหรับ
    0.35
    abody
    0.35
    ának
    0.35
    POSITIVE LOGITS
    Ư
    0.45
     cream
    0.45
     creams
    0.44
     creme
    0.43
     disorganized
    0.41
     দৌড়ে
    0.40
     childish
    0.40
     transference
    0.40
     Krem
    0.39
    cream
    0.39
    Act Density 0.002%

    No Known Activations