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
     probably
    -0.08
     "");
↵
    -0.07
    "As
    -0.07
    üzel
    -0.07
    ="")↵
    -0.07
    “As
    -0.06
    ................................................................
    -0.06
    ='')↵
    -0.06
     th�
    -0.06
    Gear
    -0.06
    POSITIVE LOGITS
    rootScope
    0.07
    -Allow
    0.06
     Magical
    0.06
     utilize
    0.06
    杰
    0.06
     юрид
    0.06
    phys
    0.06
    ARGET
    0.06
    �
    0.06
    setTimeout
    0.06
    Act Density 0.023%

    No Known Activations