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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pepper
    -0.07
    OLUTE
    -0.06
    884
    -0.06
    利用
    -0.06
    inth
    -0.06
    .events
    -0.06
     patter
    -0.06
     corridor
    -0.06
     credentials
    -0.06
    盘
    -0.06
    POSITIVE LOGITS
    news
    0.06
    ")+
    0.06
    leanup
    0.06
    ')+
    0.06
    findOrFail
    0.06
    .DataPropertyName
    0.06
    ,response
    0.06
    CHEMY
    0.06
     ocup
    0.06
    (case
    0.06
    Act Density 0.052%

    No Known Activations