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

    Neuronpedia

    INDEX
    Explanations

    story mathematics problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    签证
    -0.08
     Vander
    -0.07
     tasked
    -0.07
    𝑮
    -0.06
    GC
    -0.06
    Jennifer
    -0.06
    物业公司
    -0.06
    .�
    -0.06
    (Messages
    -0.06
     glanced
    -0.06
    POSITIVE LOGITS
    く
    0.08
    为一体
    0.07
     oriented
    0.06
    sector
    0.06
    eft
    0.06
     Ain
    0.06
     doubling
    0.06
    스트
    0.06
     Sou
    0.06
    抑制
    0.06
    Act Density 0.006%

    No Known Activations