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

    Neuronpedia

    INDEX
    Explanations

    specific characters or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     этой
    0.41
     qualcosa
    0.40
     পেয়েছিলাম
    0.40
    quela
    0.39
     digitally
    0.39
    prima
    0.37
    over
    0.36
     Dipl
    0.36
    }$
    0.36
     quella
    0.36
    POSITIVE LOGITS
    Ⲥ
    0.42
     होती
    0.39
     인한
    0.39
    カラム
    0.38
    이면
    0.38
     名前
    0.38
    厷
    0.37
    秪
    0.37
     অস্ত্র
    0.37
    રિ
    0.37
    Act Density 0.007%

    No Known Activations