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

    Neuronpedia

    INDEX
    Explanations

    indexes starting from 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .=
    0.42
    💿
    0.38
    <unused332>
    0.37
     Тен
    0.37
     lớ
    0.37
    恝
    0.37
     nó
    0.36
     ihe
    0.36
     Цуки
    0.36
    )=
    0.36
    POSITIVE LOGITS
    D
    0.44
    रा
    0.41
    er
    0.40
    ת
    0.39
    ra
    0.39
     (
    0.38
    m
    0.38
    ad
    0.38
    ↵↵
    0.38
     setempat
    0.38
    Act Density 0.261%

    No Known Activations