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

    Neuronpedia

    INDEX
    Explanations

    Circular loops

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    財
    -0.07
    呇
    -0.07
     SCREEN
    -0.06
    -paid
    -0.06
    ﺼ
    -0.06
     Junk
    -0.06
    accumulate
    -0.06
    万户
    -0.06
    ϗ
    -0.06
     nouvelle
    -0.06
    POSITIVE LOGITS
     solver
    0.09
    USA
    0.08
    olve
    0.07
    -more
    0.07
    .Result
    0.07
     dto
    0.07
    nızda
    0.07
    陛下
    0.06
    ⬤
    0.06
    机组
    0.06
    Act Density 0.013%

    No Known Activations