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

    Neuronpedia

    INDEX
    Explanations

    concepts and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ję
    0.37
    temper
    0.36
    િજા
    0.36
    لف
    0.35
    꾸
    0.35
    ]})
    0.34
    deficient
    0.34
    ṇ
    0.34
    фек
    0.34
     ያስ
    0.34
    POSITIVE LOGITS
    டித்து
    0.41
     inorder
    0.40
     Schub
    0.39
    FXML
    0.38
    不住
    0.38
     kudos
    0.38
     APPLY
    0.38
    还能
    0.37
     konsep
    0.37
    iesel
    0.37
    Act Density 0.001%

    No Known Activations