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

    Neuronpedia

    INDEX
    Explanations

    Human experimentation ethics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "struct
    -0.07
     wei
    -0.07
    빴
    -0.07
    .feature
    -0.06
     setPage
    -0.06
    課程
    -0.06
     ROW
    -0.06
     Logistic
    -0.06
    重温
    -0.06
    팠
    -0.06
    POSITIVE LOGITS
     ORIGINAL
    0.08
     techno
    0.07
    体质
    0.07
    imo
    0.07
     chir
    0.06
    不知不
    0.06
     Suppress
    0.06
    animated
    0.06
     реализаци
    0.06
    .fullName
    0.06
    Act Density 0.022%

    No Known Activations