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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ustus
    0.43
    酘
    0.41
     ies
    0.39
    த்துள்ள
    0.38
     творчества
    0.38
    ској
    0.37
     kreatif
    0.37
    новить
    0.36
     kre
    0.36
    נות
    0.36
    POSITIVE LOGITS
    p
    0.49
    zynarod
    0.43
    c
    0.43
    -
    0.42
    +,
    0.42
    +
    0.42
    bar
    0.40
     짧
    0.39
    ership
    0.39
     Cleveland
    0.38
    Act Density 0.063%

    No Known Activations