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

    Neuronpedia

    INDEX
    Explanations

    write a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ")).
    0.46
     युवाओ
    0.45
    典型的
    0.45
     တယ်
    0.45
    __."
    0.44
    Jin
    0.44
    ")),
    0.44
    *",
    0.44
    $\--
    0.44
    <unused1741>
    0.44
    POSITIVE LOGITS
    :
    0.54
    ert
    0.51
    .
    0.48
    1
    0.47
    について
    0.47
     blame
    0.46
     rag
    0.45
    (
    0.45
    aker
    0.44
     cleaned
    0.43
    Act Density 0.002%

    No Known Activations