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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toprak
    -0.08
     lehet
    -0.08
     stereo
    -0.07
     yên
    -0.07
     evening
    -0.07
    essoa
    -0.07
     suction
    -0.07
    稳
    -0.06
     fierc
    -0.06
     Zuckerberg
    -0.06
    POSITIVE LOGITS
     Lastly
    0.11
    Lastly
    0.09
     Secondly
    0.07
     Wrong
    0.06
    ,{↵
    0.06
    licate
    0.06
     кус
    0.06
     honda
    0.06
     gmail
    0.06
    %",
    0.06
    Act Density 0.005%

    No Known Activations