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

    Neuronpedia

    INDEX
    Explanations

    Moon landing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Attention
    -0.08
     attention
    -0.07
     IW
    -0.07
     SCALE
    -0.07
    ysize
    -0.07
    cono
    -0.07
     RAF
    -0.07
    .layout
    -0.07
     Gee
    -0.07
     Sanders
    -0.07
    POSITIVE LOGITS
    /star
    0.06
     повыш
    0.06
    (MediaType
    0.06
    .bootstrap
    0.06
     Liberal
    0.06
    nm
    0.06
     Elasticsearch
    0.06
    abyrin
    0.06
    擊
    0.06
    じゃ
    0.06
    Act Density 0.019%

    No Known Activations