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

    Neuronpedia

    INDEX
    Explanations

    stating facts and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nunca
    0.42
     famosos
    0.42
     jamás
    0.40
     nossos
    0.40
     herunter
    0.38
     leurs
    0.38
    相应的
    0.38
     berühm
    0.38
     niezwy
    0.38
     oppure
    0.37
    POSITIVE LOGITS
     Presumably
    0.74
     presumably
    0.67
    presumably
    0.61
    とのこと
    0.61
     вашем
    0.57
     ваш
    0.52
    하신
    0.52
     যেহেতু
    0.51
     sounds
    0.50
     Ваш
    0.50
    Act Density 0.025%

    No Known Activations