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

    Neuronpedia

    INDEX
    Explanations

    qualifications and clarifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uninstall
    0.44
    什么
    0.41
    لە
    0.41
    ศึกษา
    0.40
    {~
    0.40
     nginx
    0.40
    山东
    0.39
     Correctional
    0.38
    }
    0.38
     나올
    0.38
    POSITIVE LOGITS
    פר
    0.46
    טר
    0.45
    كبر
    0.45
    Particular
    0.43
    кова
    0.43
    нка
    0.42
    CLASSI
    0.42
    ADI
    0.42
    роз
    0.41
    קה
    0.41
    Act Density 0.004%

    No Known Activations