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

    Neuronpedia

    INDEX
    Explanations

    Romanian language and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Debido
    0.80
    håll
    0.76
    alay
    0.76
     イ
    0.73
     ਵਿ
    0.72
     Mens
    0.71
     Faites
    0.71
     INDUST
    0.71
    ർ
    0.71
    ír
    0.70
    POSITIVE LOGITS
     tot
    0.74
     mere
    0.71
     o
    0.66
    和一个
    0.65
     meteen
    0.64
     едва
    0.64
     ceva
    0.63
     inkább
    0.62
     rapid
    0.61
    แค่
    0.60
    Act Density 0.001%

    No Known Activations