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

    Neuronpedia

    INDEX
    Explanations

    financial markets, crypto, programming, and other specific subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    0.90
    er
    0.81
    the
    0.80
    de
    0.79
    ard
    0.75
    du
    0.72
    line
    0.72
    in
    0.71
    IN
    0.71
    st
    0.71
    POSITIVE LOGITS
    glightbox
    0.94
    ພວກເຮ
    0.91
     hacemos
    0.90
     ignoreString
    0.88
     bactéries
    0.88
    бавля
    0.86
    ポーター
    0.86
     فولت
    0.86
    ᅪ
    0.86
    欷
    0.84
    Act Density 0.002%

    No Known Activations