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

    Neuronpedia

    INDEX
    Explanations

    I can help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     гаранти
    0.48
     можно
    0.47
    你可以
    0.46
     می‌توانید
    0.45
    ampions
    0.44
     можна
    0.44
    Disponible
    0.44
    สามารถ
    0.44
    abilirsiniz
    0.44
    您可以
    0.44
    POSITIVE LOGITS
     psychos
    0.44
    肯定是
    0.44
     kritis
    0.42
     chariot
    0.41
     gluon
    0.41
     bibliography
    0.40
     pasti
    0.40
     ajuda
    0.39
     Helps
    0.39
     homot
    0.39
    Act Density 0.058%

    No Known Activations