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

    Neuronpedia

    INDEX
    Explanations

    data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     latitude
    -0.07
     ста
    -0.07
    rotch
    -0.07
     battlefield
    -0.07
    Edge
    -0.06
     riots
    -0.06
     distress
    -0.06
     alcohol
    -0.06
    Yaw
    -0.06
     Enterprise
    -0.06
    POSITIVE LOGITS
    =back
    0.08
    اورپ
    0.06
     Thailand
    0.06
    ंस
    0.06
    -generated
    0.06
     beaut
    0.06
     LinkedHashMap
    0.06
    .jsx
    0.06
     hack
    0.06
    上的
    0.06
    Act Density 0.037%

    No Known Activations