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

    Neuronpedia

    INDEX
    Explanations

    Code/Strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (keys
    -0.07
     starttime
    -0.06
     NOW
    -0.06
    .content
    -0.06
     Rever
    -0.06
     Universities
    -0.06
    姆
    -0.06
     پیچ
    -0.06
     фас
    -0.06
    _CPU
    -0.06
    POSITIVE LOGITS
    олай
    0.08
    ERING
    0.07
    _TRIANGLES
    0.07
    UREMENT
    0.07
    /person
    0.06
    asal
    0.06
     serde
    0.06
    Dice
    0.06
    _Game
    0.06
    _Tree
    0.06
    Act Density 0.066%

    No Known Activations