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

    Neuronpedia

    INDEX
    Explanations

    technical terms and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    melon
    0.45
    﨑
    0.39
    pipe
    0.38
    ́
    0.38
    法语
    0.38
    mfrac
    0.38
    ാപ
    0.38
    tow
    0.38
     Melon
    0.38
     ვ
    0.37
    POSITIVE LOGITS
    UMENTS
    0.41
    rians
    0.37
     Rabat
    0.37
     امت
    0.36
     PASSWORD
    0.36
    ServiceName
    0.36
    ής
    0.35
     পরিচাল
    0.35
    Tasty
    0.35
    पहर
    0.35
    Act Density 0.000%

    No Known Activations