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

    Neuronpedia

    INDEX
    Explanations

    .min

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    胄
    -0.07
    InChildren
    -0.07
    cells
    -0.07
    .sort
    -0.07
    幼儿
    -0.07
     Gian
    -0.07
    持ち
    -0.07
    不经意
    -0.07
     xcb
    -0.06
    Sure
    -0.06
    POSITIVE LOGITS
    >("
    0.08
    คม
    0.07
     namespaces
    0.07
    _thresh
    0.07
     distorted
    0.07
    ностей
    0.07
     reform
    0.07
    团结
    0.07
    扭矩
    0.07
    _PULL
    0.07
    Act Density 0.001%

    No Known Activations