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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    consin
    -0.07
    _WALL
    -0.06
    ์)
    -0.06
     Tale
    -0.06
    대표
    -0.06
    (user
    -0.06
     DatabaseReference
    -0.06
     DON
    -0.06
    ﻮ
    -0.06
    $/)
    -0.06
    POSITIVE LOGITS
    окумент
    0.07
     Extend
    0.07
    aket
    0.07
     craving
    0.07
    纸
    0.07
     Mock
    0.06
     jMenuItem
    0.06
     verbally
    0.06
    oad
    0.06
    unan
    0.06
    Act Density 0.001%

    No Known Activations