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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edx
    -0.07
    <src
    -0.07
    מוסר
    -0.06
     crianças
    -0.06
     sober
    -0.06
     gql
    -0.06
    眭
    -0.06
    �
    -0.06
    overe
    -0.06
    builders
    -0.06
    POSITIVE LOGITS
    刺激
    0.08
     contamination
    0.08
    _finish
    0.07
    Defaults
    0.07
    _hist
    0.07
    Unmount
    0.07
     Begin
    0.07
     HELP
    0.07
     olmadığı
    0.07
    过户
    0.07
    Act Density 0.010%

    No Known Activations