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

    Neuronpedia

    INDEX
    Explanations

    code string quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вається
    0.82
    läuft
    0.77
    количество
    0.75
    ែម
    0.75
     борьбе
    0.75
    ުޅ
    0.73
    kj
    0.73
    личество
    0.72
     pytest
    0.72
     нер
    0.71
    POSITIVE LOGITS
     ""
    2.36
     "";
    1.98
     "",
    1.96
     "[
    1.87
     ''
    1.85
     '"
    1.83
    ""
    1.79
     “‘
    1.78
     “”
    1.77
     "'
    1.76
    Act Density 0.419%

    No Known Activations