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

    Neuronpedia

    INDEX
    Explanations

    Healthy product descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arget
    -0.07
    .ut
    -0.07
     původ
    -0.07
     nově
    -0.07
     fullName
    -0.06
    第一
    -0.06
     stabbing
    -0.06
    gt
    -0.06
    ัด
    -0.06
     частини
    -0.06
    POSITIVE LOGITS
     UserDao
    0.07
     έργ
    0.06
    ={{↵
    0.06
    (Seq
    0.06
     เว
    0.06
    .ForEach
    0.06
    stakes
    0.06
     boj
    0.06
     Enumeration
    0.06
    	cal
    0.06
    Act Density 0.015%

    No Known Activations