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

    Neuronpedia

    INDEX
    Explanations

    Programming data types

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unordered
    -0.07
    opts
    -0.06
     letters
    -0.06
     tur
    -0.06
     sweets
    -0.06
     secretly
    -0.06
     làm
    -0.06
    Food
    -0.06
     weather
    -0.06
     originally
    -0.06
    POSITIVE LOGITS
    licts
    0.06
     detay
    0.06
    스터
    0.06
    uais
    0.06
    coe
    0.06
    진
    0.06
    �제
    0.06
     ře
    0.06
     Ronald
    0.06
     knull
    0.06
    Act Density 0.032%

    No Known Activations