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
    ."/
    -0.08
    发布会
    -0.07
    ểu
    -0.07
     Vit
    -0.07
     railing
    -0.07
     Lonely
    -0.07
    !'
    -0.07
    جار
    -0.06
     glyc
    -0.06
    .WEST
    -0.06
    POSITIVE LOGITS
     المغرب
    0.08
    _RATIO
    0.07
    Taken
    0.07
    checking
    0.07
     creed
    0.07
     droits
    0.06
    OLUMN
    0.06
    ﻇ
    0.06
    ellation
    0.06
    insn
    0.06
    Act Density 0.001%

    No Known Activations