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

    Neuronpedia

    INDEX
    Explanations

    previous performance, experiences, or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    1.02
    加え
    1.00
     ομά
    0.98
    ?
    0.96
    り
    0.94
     integrada
    0.93
    ری
    0.92
     I
    0.90
    あ
    0.90
    กับ
    0.89
    POSITIVE LOGITS
    تان
    1.02
    е
    1.00
    tedir
    0.97
    ней
    0.95
    اية
    0.89
    с
    0.89
    هما
    0.87
    م
    0.87
    اك
    0.86
    ا
    0.85
    Act Density 0.028%

    No Known Activations