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

    Neuronpedia

    INDEX
    Explanations

    origins and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nếu
    0.68
     éviter
    0.59
     eventuali
    0.58
     evitare
    0.58
     puedan
    0.57
     جلوگیری
    0.55
     empêcher
    0.54
     pouvaient
    0.54
     если
    0.54
     deben
    0.54
    POSITIVE LOGITS
     Founded
    0.80
    Founded
    0.79
     headquartered
    0.79
     history
    0.71
     originated
    0.70
     founded
    0.69
    originally
    0.68
     törté
    0.67
     debuted
    0.66
     renowned
    0.64
    Act Density 0.609%

    No Known Activations