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

    Neuronpedia

    INDEX
    Explanations

    .to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DOWN
    -0.07
    =view
    -0.07
     Parker
    -0.07
     •
    -0.07
    Regional
    -0.06
    aved
    -0.06
     effet
    -0.06
     ri
    -0.06
    けて
    -0.06
    Chars
    -0.06
    POSITIVE LOGITS
    .to
    0.08
     San
    0.07
    Louis
    0.06
     cucumber
    0.06
    坂
    0.06
     illustrator
    0.06
    .SERVER
    0.06
     설정
    0.06
     architects
    0.06
     와
    0.06
    Act Density 0.001%

    No Known Activations