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

    Neuronpedia

    INDEX
    Explanations

    helping verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hait
    -0.06
    ฎ
    -0.06
    ungal
    -0.06
     beds
    -0.06
     Lup
    -0.06
     reel
    -0.06
    新
    -0.06
    Employee
    -0.06
    存于
    -0.06
     Swim
    -0.06
    POSITIVE LOGITS
    [top
    0.07
     {/*
    0.07
     underneath
    0.07
     *))
    0.07
    .........
    0.06
    [^
    0.06
    ─
    0.06
    exceptions
    0.06
     ____
    0.06
     government
    0.06
    Act Density 0.111%

    No Known Activations