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

    Neuronpedia

    INDEX
    Explanations

    remote Diagnostics and monitoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رجل
    0.46
    Цена
    0.46
     disponibilidade
    0.45
    Alcohol
    0.45
     Constru
    0.44
    ूहिक
    0.44
    Между
    0.44
    书法
    0.44
    0.44
    Drug
    0.44
    POSITIVE LOGITS
     already
    0.52
     exclusion
    0.47
     files
    0.46
     undermining
    0.46
     parties
    0.46
     periods
    0.46
     action
    0.45
     improvements
    0.45
     operating
    0.45
     earning
    0.45
    Act Density 0.000%

    No Known Activations