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

    Neuronpedia

    INDEX
    Explanations

    word counts or lengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ثاني
    0.46
     Steve
    0.42
     Goll
    0.42
     Rebecca
    0.42
     Zal
    0.42
    CIS
    0.41
     リュ
    0.41
    Steve
    0.41
    ➋
    0.40
     Janssen
    0.40
    POSITIVE LOGITS
     aldrig
    0.40
     זה
    0.40
    աք
    0.39
     cyclase
    0.39
     Keywords
    0.38
     mentality
    0.37
    ্ষিকী
    0.37
     slav
    0.36
    قول
    0.36
    本書
    0.36
    Act Density 0.000%

    No Known Activations