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

    Neuronpedia

    INDEX
    Explanations

    help with compulsive behaviors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تيجة
    0.42
    usepackage
    0.41
    Bibliography
    0.40
     mathbf
    0.37
    的情况
    0.36
    可以是
    0.36
    ^
    0.36
     equation
    0.36
     cần
    0.35
    原始内容存档
    0.35
    POSITIVE LOGITS
    affordable
    0.43
    ссив
    0.41
     affordable
    0.41
     LLC
    0.41
     především
    0.40
    fasst
    0.39
     propriétaires
    0.39
     nonprofit
    0.39
     eszköz
    0.39
     компании
    0.38
    Act Density 0.059%

    No Known Activations