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

    Neuronpedia

    INDEX
    Explanations

    certificate signing, pinning, authority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    1.20
    ك
    1.10
    ня
    1.08
    .
    1.02
     cisplatin
    0.96
     повы
    0.95
    नी
    0.95
     बढ़ने
    0.94
     σειρά
    0.92
    赜
    0.90
    POSITIVE LOGITS
    ле
    1.29
    in
    1.22
    remove
    1.05
    ow
    1.02
    ut
    1.01
    st
    1.00
    ler
    0.94
    has
    0.93
    ↵
    0.92
    for
    0.92
    Act Density 0.005%

    No Known Activations