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

    Neuronpedia

    INDEX
    Explanations

    offering elaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etc
    0.92
    etc
    0.88
    Our
    0.82
     etcétera
    0.79
     usw
    0.79
     وغیرہ
    0.78
     Our
    0.74
    תיים
    0.73
    ご理解
    0.72
    등
    0.72
    POSITIVE LOGITS
     axit
    0.69
     History
    0.68
    ;'>
    0.67
     subsequ
    0.67
     Informatics
    0.67
     Information
    0.67
    لومات
    0.66
    History
    0.66
     Informations
    0.65
     வரலாறு
    0.65
    Act Density 0.046%

    No Known Activations