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

    Neuronpedia

    INDEX
    Explanations

    sub

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $("#"
    -0.06
     article
    -0.06
    '↵
    -0.06
    ी↵
    -0.06
     ferr
    -0.06
    .rate
    -0.06
     miesz
    -0.06
    ЕТ
    -0.06
     ""))↵
    -0.06
    /)
    -0.06
    POSITIVE LOGITS
    _Sub
    0.07
    (mapped
    0.06
    (itemId
    0.06
    web
    0.06
    任何
    0.06
    -President
    0.06
    pNet
    0.06
    有什么
    0.06
    ationToken
    0.06
    ευ
    0.06
    Act Density 0.002%

    No Known Activations