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

    Neuronpedia

    INDEX
    Explanations

    lora

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Use
    0.39
    窅
    0.38
    ächlich
    0.36
    angal
    0.36
    +][
    0.36
    ల్య
    0.36
    yao
    0.35
    🔜
    0.35
     produk
    0.35
     Employment
    0.35
    POSITIVE LOGITS
     lor
    0.52
    raine
    0.51
     Lor
    0.42
    azepam
    0.41
    rained
    0.40
    Lor
    0.39
    iral
    0.36
    LOR
    0.35
    اکہ
    0.34
     चोरी
    0.34
    Act Density 0.002%

    No Known Activations