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

    Neuronpedia

    INDEX
    Explanations

    scientific research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .presenter
    -0.07
    招商引
    -0.06
    💠
    -0.06
     recorded
    -0.06
    滏
    -0.06
     wyposaż
    -0.06
    ⍩
    -0.06
    棻
    -0.06
    HostException
    -0.06
    ✼
    -0.06
    POSITIVE LOGITS
    买
    0.08
    exampleInputEmail
    0.08
     cyclic
    0.07
     wholesome
    0.07
    ambda
    0.07
    _UTIL
    0.07
    巧妙
    0.07
    한다고
    0.07
    最喜欢
    0.07
     qr
    0.07
    Act Density 0.043%

    No Known Activations