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

    Neuronpedia

    INDEX
    Explanations

    fatty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dr
    -0.08
     AppMethodBeat
    -0.08
     Zw
    -0.07
    ゛
    -0.07
    还包括
    -0.07
     знач
    -0.07
     Chennai
    -0.07
    米饭
    -0.07
    調べ
    -0.07
     Burger
    -0.06
    POSITIVE LOGITS
     Lyons
    0.07
    Singleton
    0.07
    Blob
    0.07
    姑
    0.06
    Clip
    0.06
    LIB
    0.06
    פתיחת
    0.06
    IAL
    0.06
     goal
    0.06
     gods
    0.06
    Act Density 0.008%

    No Known Activations