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
     socks
    -0.07
     '/')↵
    -0.07
     '{@
    -0.07
     Declare
    -0.07
    contre
    -0.07
    ∪
    -0.06
    꽌
    -0.06
     bamb
    -0.06
    噪
    -0.06
     almond
    -0.06
    POSITIVE LOGITS
    =\""
    0.07
    units
    0.07
    仍是
    0.07
     nhẹ
    0.07
    LLLL
    0.07
    licity
    0.07
    四川省
    0.06
    峃
    0.06
    的道理
    0.06
    Enemies
    0.06
    Act Density 0.002%

    No Known Activations