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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    puter
    -0.07
     maximizing
    -0.07
    stackpath
    -0.06
     conditioner
    -0.06
     आदम
    -0.06
    beros
    -0.06
    nant
    -0.06
     nes
    -0.06
    ites
    -0.06
     computing
    -0.05
    POSITIVE LOGITS
    +↵
    0.08
    irect
    0.07
    ename
    0.07
     glUniform
    0.07
     amore
    0.07
    _fin
    0.07
    etty
    0.07
     birinin
    0.07
    ?↵↵↵
    0.07
     AABB
    0.07
    Act Density 0.147%

    No Known Activations