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

    Neuronpedia

    INDEX
    Explanations

    bad concerning unethical illegal actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hoặc
    1.11
     или
    1.03
     atau
    1.02
     या
    1.00
    하거나
    1.00
     किंवा
    0.99
     or
    0.97
    したり
    0.96
    或
    0.95
     یا
    0.93
    POSITIVE LOGITS
     শি
    0.73
     furthermore
    0.72
     moreover
    0.71
     बढ़ाता
    0.70
     στά
    0.68
     veuillez
    0.68
    帮
    0.67
     DriverManager
    0.66
     além
    0.66
    你应该
    0.65
    Act Density 0.255%

    No Known Activations