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

    Neuronpedia

    INDEX
    Explanations

    words to happen to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.55
    .**
    0.55
    です
    0.53
    는
    0.53
     mounting
    0.53
    .*
    0.51
    ？
    0.50
    .|
    0.50
    -
    0.50
    。
    0.50
    POSITIVE LOGITS
     Filing
    0.65
    ैनल
    0.63
     Sebelum
    0.62
    Tcp
    0.61
    Adv
    0.60
     Tcp
    0.60
     Según
    0.59
     Bc
    0.58
     Relig
    0.58
     Чтобы
    0.58
    Act Density 0.000%

    No Known Activations