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

    Neuronpedia

    INDEX
    Explanations

    Identification, medical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    热点
    -0.07
     smarter
    -0.07
    干嘛
    -0.07
     disarm
    -0.07
    สะสม
    -0.07
    女朋友
    -0.07
    妝
    -0.07
     incom
    -0.06
     степени
    -0.06
    過ぎ
    -0.06
    POSITIVE LOGITS
     Herrera
    0.07
     BY
    0.07
    ostringstream
    0.07
     fluid
    0.07
     Bảo
    0.07
     INTO
    0.07
     Shaft
    0.07
    mesh
    0.07
    Clause
    0.07
     Pública
    0.07
    Act Density 0.001%

    No Known Activations