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

    Neuronpedia

    INDEX
    Explanations

    confined

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ycles
    -0.07
    路径
    -0.07
     thật
    -0.06
     забезпеч
    -0.06
     signaled
    -0.06
    росто
    -0.06
    Vertex
    -0.06
    leurs
    -0.06
     disregard
    -0.06
     enter
    -0.06
    POSITIVE LOGITS
     행정
    0.08
     confined
    0.08
     openid
    0.07
     Af
    0.07
     Confeder
    0.07
     Concurrent
    0.07
    ycopg
    0.07
    ��
    0.07
     Cognitive
    0.06
     Ko
    0.06
    Act Density 0.003%

    No Known Activations