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

    Neuronpedia

    INDEX
    Explanations

    Character introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forest
    -0.07
     rpc
    -0.07
     venom
    -0.07
     Msg
    -0.07
     breakdown
    -0.07
     adulthood
    -0.06
     LED
    -0.06
     Ying
    -0.06
     člově
    -0.06
    _IO
    -0.06
    POSITIVE LOGITS
    ="@
    0.06
    [image
    0.06
    _feedback
    0.06
     ισχ
    0.06
    =[]↵
    0.06
     apresent
    0.06
     край
    0.06
    CKET
    0.06
    )';↵
    0.06
     breat
    0.06
    Act Density 0.047%

    No Known Activations