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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     />'
    -0.08
    焙
    -0.07
     evolves
    -0.07
    낙
    -0.07
     보기
    -0.07
     Lad
    -0.07
     evoke
    -0.06
    젠
    -0.06
    你还
    -0.06
    前进
    -0.06
    POSITIVE LOGITS
     Hidden
    0.07
    =len
    0.07
    arring
    0.07
    ,false
    0.07
    uffles
    0.07
    רוצה
    0.07
    tractor
    0.07
    átis
    0.07
    .arm
    0.07
    _current
    0.07
    Act Density 0.001%

    No Known Activations