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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nature
    -0.07
    h
    -0.07
    istring
    -0.07
     has
    -0.07
    _board
    -0.06
    _routes
    -0.06
    hl
    -0.06
    ul
    -0.06
    VEL
    -0.06
    ame
    -0.06
    POSITIVE LOGITS
    พน
    0.06
     Associated
    0.06
     plagiar
    0.06
    ์การ
    0.06
    無料
    0.06
    ']}</
    0.06
    ('.',
    0.06
     znač
    0.06
     blown
    0.06
    ا�
    0.06
    Act Density 0.081%

    No Known Activations