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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BufferData
    -0.08
     */,
    -0.07
     font
    -0.07
     bounded
    -0.07
    所以他
    -0.07
     loneliness
    -0.07
    炻
    -0.07
    Found
    -0.07
    ollipop
    -0.07
     gps
    -0.07
    POSITIVE LOGITS
    ؏
    0.07
    .Messaging
    0.07
     flight
    0.07
    .Custom
    0.06
    뵀
    0.06
    校
    0.06
    对标
    0.06
    ('.
    0.06
     sights
    0.06
    一旦
    0.06
    Act Density 0.052%

    No Known Activations