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

    Neuronpedia

    INDEX
    Explanations

    resource

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    特定
    -0.07
    Proc
    -0.07
    America
    -0.07
    ingleton
    -0.06
     fools
    -0.06
    _fd
    -0.06
    填补
    -0.06
    сет
    -0.06
    給
    -0.06
     scholars
    -0.06
    POSITIVE LOGITS
    칟
    0.07
     deficient
    0.07
    _Detail
    0.07
    Compar
    0.06
    𝐥
    0.06
    אב
    0.06
    /options
    0.06
     viện
    0.06
    ضغ
    0.06
    昳
    0.06
    Act Density 0.009%

    No Known Activations