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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IPLE
    -0.07
    립
    -0.06
    .semantic
    -0.06
    <Point
    -0.06
     discoveries
    -0.06
     merit
    -0.06
    allocate
    -0.06
    іла
    -0.06
    +Sans
    -0.06
     dealers
    -0.06
    POSITIVE LOGITS
    course
    0.08
    исс
    0.06
     già
    0.06
     उसक
    0.06
    ниц
    0.06
     매매가
    0.06
     داخ
    0.06
    ีเด
    0.06
    한국
    0.06
    088
    0.06
    Act Density 0.130%

    No Known Activations