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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bei
    -0.07
     Proposal
    -0.07
     Sean
    -0.06
     پاک
    -0.06
    ,result
    -0.06
     openid
    -0.06
     Question
    -0.06
    .Do
    -0.06
     Defaults
    -0.06
     turns
    -0.06
    POSITIVE LOGITS
    sdale
    0.07
    lichkeit
    0.07
     متن
    0.06
    namespace
    0.06
     cuanto
    0.06
    orable
    0.06
    <Scalar
    0.06
     lest
    0.06
     investigating
    0.06
    ful
    0.06
    Act Density 0.005%

    No Known Activations