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

    Neuronpedia

    INDEX
    Explanations

    X or Y structures, comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েও
    0.48
    ה
    0.43
    a
    0.42
     возмо
    0.41
     C
    0.41
    ه
    0.40
    好吃
    0.40
     Charlie
    0.39
    in
    0.39
    i
    0.39
    POSITIVE LOGITS
    ल
    0.41
    ਾ
    0.41
    Université
    0.41
    чені
    0.40
    ПР
    0.39
    ﺪ
    0.39
    Macrophages
    0.38
    Storia
    0.38
    Viewer
    0.38
    Proveedor
    0.38
    Act Density 0.416%

    No Known Activations