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

    Neuronpedia

    INDEX
    Explanations

    thick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    νας
    -0.07
     안전
    -0.07
    _PHONE
    -0.06
    _PREF
    -0.06
     dự
    -0.06
    スタ
    -0.06
    Cost
    -0.06
    uracy
    -0.06
    슈
    -0.06
     độc
    -0.06
    POSITIVE LOGITS
     gluten
    0.07
    ,...↵↵
    0.06
     oven
    0.06
     congrat
    0.06
     lint
    0.06
    idue
    0.06
     carry
    0.06
     ض
    0.06
     Which
    0.06
    %
↵
    0.06
    Act Density 0.003%

    No Known Activations