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

    Neuronpedia

    INDEX
    Explanations

    active

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    愫
    -0.08
    .nn
    -0.08
     Km
    -0.07
    ReactDOM
    -0.07
    谳
    -0.07
    电线
    -0.07
    סטודנט
    -0.07
    .init
    -0.07
    [N
    -0.07
    萩
    -0.07
    POSITIVE LOGITS
    처
    0.08
    Active
    0.08
     CE
    0.07
    structions
    0.07
    'al
    0.07
    魏
    0.07
    对应的
    0.06
    _remote
    0.06
     attendance
    0.06
    冲
    0.06
    Act Density 0.014%

    No Known Activations