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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    갈
    -0.08
    낏
    -0.07
    asil
    -0.07
     pilots
    -0.07
    itive
    -0.07
    !]
    -0.07
    짥
    -0.07
    巾
    -0.07
    zza
    -0.07
    usp
    -0.06
    POSITIVE LOGITS
     Evo
    0.07
    的利益
    0.07
    EventManager
    0.07
    研究
    0.07
     Baylor
    0.06
     Concat
    0.06
     Presbyterian
    0.06
    关键
    0.06
    主要有
    0.06
     Inf
    0.06
    Act Density 0.002%

    No Known Activations