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

    Neuronpedia

    INDEX
    Explanations

    closing issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вка
    0.40
     নৃ
    0.39
    ಪ್ಪು
    0.37
    ollipop
    0.36
     انہ
    0.36
    ادات
    0.36
    ابات
    0.36
    הר
    0.36
     hazel
    0.35
    राई
    0.35
    POSITIVE LOGITS
     closed
    0.83
     issues
    0.78
     issue
    0.71
     Closed
    0.71
    Issues
    0.71
    issue
    0.70
    Closed
    0.70
     closing
    0.70
     Issues
    0.70
    closed
    0.67
    Act Density 0.005%

    No Known Activations