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

    Neuronpedia

    INDEX
    Explanations

    numbers, symbols, and various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     అన్ని
    0.57
     Allergy
    0.52
    Indexs
    0.51
     Министерства
    0.51
     भंड
    0.49
    𝙄
    0.48
     专业
    0.48
    车站
    0.48
    Loans
    0.48
     акты
    0.47
    POSITIVE LOGITS
    <0x80>
    0.64
     terceiro
    0.49
    बाह
    0.47
    ३
    0.46
    to
    0.45
    பிர
    0.44
    ்தான்
    0.43
    кови
    0.43
     leído
    0.43
    νου
    0.43
    Act Density 0.000%

    No Known Activations