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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /,
    -0.08
     Bounty
    -0.07
    ,//
    -0.07
     various
    -0.07
    Import
    -0.06
    뮌
    -0.06
     DNS
    -0.06
    _test
    -0.06
    缶
    -0.06
     departed
    -0.06
    POSITIVE LOGITS
    Prompt
    0.07
    апример
    0.07
    _pts
    0.07
     Gefühl
    0.07
    将于
    0.07
    =options
    0.07
    _FIRST
    0.07
     infos
    0.07
    egt
    0.07
     InvalidOperationException
    0.07
    Act Density 0.023%

    No Known Activations