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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чі
    -0.06
     sorter
    -0.06
     wie
    -0.06
    üslü
    -0.06
    在
    -0.06
    _agents
    -0.06
    (sys
    -0.06
    _aligned
    -0.06
    '>{
    -0.06
    -0.06
    POSITIVE LOGITS
     specification
    0.07
     },{↵
    0.07
     dost
    0.07
     그것
    0.06
     limitation
    0.06
    (Call
    0.06
     chữ
    0.06
    //---------------------------------------------------------------------------↵
    0.06
    \Controller
    0.06
     unsuccessfully
    0.06
    Act Density 0.020%
    No Known Activations