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

    Neuronpedia

    INDEX
    Explanations

    say the ending -ings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    택
    -0.08
     ticks
    -0.07
     c
    -0.07
    xl
    -0.07
    _TAC
    -0.07
    归来
    -0.07
    视线
    -0.06
    ㏜
    -0.06
    戾
    -0.06
    (section
    -0.06
    POSITIVE LOGITS
     INTER
    0.07
     이야
    0.07
     possesses
    0.07
     Interior
    0.07
    |min
    0.07
    .es
    0.07
     Israel
    0.07
    进出口
    0.06
    仅仅是
    0.06
     Dresses
    0.06
    Act Density 0.001%

    No Known Activations