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

    Neuronpedia

    INDEX
    Explanations

    say "-r"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Examples
    -0.07
    .phoneNumber
    -0.07
    Fra
    -0.06
    /navigation
    -0.06
    δει
    -0.06
    Received
    -0.06
    ipo
    -0.06
     expertise
    -0.06
     firstName
    -0.06
     infinitely
    -0.06
    POSITIVE LOGITS
     higher
    0.07
     SIMPLE
    0.07
     алког
    0.06
     subsid
    0.06
     sql
    0.06
     EnumerableStream
    0.06
    {},↵
    0.06
    아서
    0.06
     слу
    0.06
    _XDECREF
    0.06
    Act Density 0.001%

    No Known Activations