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

    Neuronpedia

    INDEX
    Explanations

    long-running operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کردار
    0.41
     character
    0.39
    ẃ
    0.39
    間の
    0.39
     கதாபா
    0.38
    тоо
    0.38
     캐릭터
    0.38
    ве
    0.37
     चरित्र
    0.37
     किरदार
    0.37
    POSITIVE LOGITS
     пари
    0.42
     punten
    0.39
    lbrack
    0.38
    umerate
    0.38
    èses
    0.37
     Collect
    0.36
    änglich
    0.36
    ெடுக்க
    0.36
    ulins
    0.36
    èges
    0.36
    Act Density 0.001%

    No Known Activations