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

    Neuronpedia

    INDEX
    Explanations

    Various subjects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﺎ
    -0.08
    就是这样
    -0.08
    🥗
    -0.07
    ıy
    -0.07
    şe
    -0.07
    (PATH
    -0.07
    的一大
    -0.07
    ᵌ
    -0.07
     AssemblyProduct
    -0.07
     distraction
    -0.07
    POSITIVE LOGITS
    加盟商
    0.07
    _SOC
    0.07
     survivors
    0.07
     comerc
    0.07
     Lotus
    0.07
     merc
    0.07
    paralle
    0.07
     sessuali
    0.06
    sink
    0.06
    رسم
    0.06
    Act Density 0.067%

    No Known Activations