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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awcy
    0.38
    ärk
    0.36
    badan
    0.36
    }=(-
    0.35
     boosting
    0.34
    send
    0.33
    പേ
    0.33
    odbc
    0.33
    companies
    0.33
    ogni
    0.33
    POSITIVE LOGITS
     ۱۳۹
    0.40
     Wörter
    0.39
     Grade
    0.38
    Grade
    0.38
     Edited
    0.38
    几年
    0.38
    小学生
    0.38
     edited
    0.38
    GRADE
    0.37
     Juillet
    0.37
    Act Density 0.000%

    No Known Activations