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

    Neuronpedia

    INDEX
    Explanations

    attachments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nx
    -0.07
    .Activity
    -0.06
     Tib
    -0.06
     \/
    -0.06
     hẳn
    -0.06
     nim
    -0.06
    建立起
    -0.06
     '|
    -0.06
     JM
    -0.06
     （
    -0.06
    POSITIVE LOGITS
    rot
    0.07
     segments
    0.07
    海岸
    0.07
    HA
    0.07
    春夏
    0.06
    变更
    0.06
     sw
    0.06
    囔
    0.06
     영화
    0.06
    allas
    0.06
    Act Density 0.002%

    No Known Activations