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

    Neuronpedia

    INDEX
    Explanations

    coming and going

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reuni
    0.38
     Named
    0.36
     runners
    0.35
    秘书
    0.35
     proximity
    0.35
     Mercedes
    0.34
     secretary
    0.34
     cashier
    0.33
     dudes
    0.33
     gaining
    0.33
    POSITIVE LOGITS
    不斷
    0.43
     ይ
    0.38
    BSCRIBE
    0.38
     abate
    0.38
    сль
    0.38
    andel
    0.37
     села
    0.37
     ይሰ
    0.37
    ти
    0.36
     оценка
    0.35
    Act Density 0.003%

    No Known Activations