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

    Neuronpedia

    INDEX
    Explanations

    numerical codes and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     circul
    0.42
     bosque
    0.41
     reassured
    0.40
    菄
    0.40
    得很
    0.39
     sceptical
    0.38
     допомо
    0.38
     sonda
    0.38
     conden
    0.37
     dedicada
    0.37
    POSITIVE LOGITS
     sayılı
    0.51
    +
    0.45
    ↵
    0.45
    bit
    0.44
    mAh
    0.44
    ，
    0.44
     mAh
    0.44
    MHz
    0.41
    억원
    0.40
     act
    0.40
    Act Density 0.049%

    No Known Activations