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

    Neuronpedia

    INDEX
    Explanations

    It

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    派
    -0.07
    زام
    -0.06
    ?family
    -0.06
     seb
    -0.06
     กรกฎาคม
    -0.06
     були
    -0.06
    segment
    -0.06
    .debian
    -0.06
     الأف
    -0.06
    .Upload
    -0.06
    POSITIVE LOGITS
    scar
    0.07
     estate
    0.07
     emotional
    0.07
     monetary
    0.07
    letters
    0.07
     атмос
    0.07
    чого
    0.06
     dễ
    0.06
    >',↵
    0.06
     标
    0.06
    Act Density 0.035%

    No Known Activations