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

    Neuronpedia

    INDEX
    Explanations

    Memory allocation size (2,5,9)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oine
    -0.08
    寞
    -0.07
    很开心
    -0.07
    UpDown
    -0.07
    箦
    -0.07
     bev
    -0.07
    (minutes
    -0.07
    .In
    -0.07
     Caroline
    -0.07
    ママ
    -0.07
    POSITIVE LOGITS
    _Ch
    0.07
    胜
    0.07
     Pu
    0.07
    /')↵
    0.06
    LoginPage
    0.06
    .arg
    0.06
     poj
    0.06
     loop
    0.06
    眼角
    0.06
     transfers
    0.06
    Act Density 0.007%

    No Known Activations