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

    Neuronpedia

    INDEX
    Explanations

    copying from or common analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ম্প
    0.41
    之处
    0.39
     DCHECK
    0.39
    ర్
    0.39
    ្ខ
    0.39
     bại
    0.38
    /'.$
    0.38
    らった
    0.38
    食
    0.38
    dates
    0.36
    POSITIVE LOGITS
    BOLD
    0.40
     Burgos
    0.39
    Bras
    0.39
    UTO
    0.37
    Especially
    0.37
    Desen
    0.36
     Selle
    0.36
    Bueno
    0.35
    infi
    0.35
    eko
    0.35
    Act Density 0.000%

    No Known Activations