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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     làng
    -0.06
    _visit
    -0.06
     =================================================
    -0.06
     ند
    -0.06
    Spe
    -0.06
    "))
    -0.06
    だろう
    -0.06
    _SAMPLE
    -0.06
    .guild
    -0.06
    friends
    -0.05
    POSITIVE LOGITS
    estruction
    0.07
     أما
    0.06
    싱
    0.06
    PathComponent
    0.06
    chapter
    0.06
     способ
    0.06
    .creation
    0.06
    accounts
    0.06
    ما
    0.06
    郑
    0.06
    Act Density 0.001%

    No Known Activations