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

    Neuronpedia

    INDEX
    Explanations

    meaning, intent, explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zusch
    0.49
     andra
    0.48
     ihres
    0.47
    AGES
    0.45
     nhảy
    0.45
    rakash
    0.44
     novem
    0.44
    UARY
    0.44
    uacute
    0.44
     Zert
    0.44
    POSITIVE LOGITS
    жение
    0.51
    ן
    0.44
     diligence
    0.44
    醂
    0.43
    ิ่น
    0.43
    一位
    0.43
    த்திரம்
    0.43
     substance
    0.43
     diligent
    0.42
    ರಿಂದ
    0.42
    Act Density 0.001%

    No Known Activations