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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oader
    -0.08
     squeeze
    -0.08
     squeezing
    -0.08
     bedside
    -0.08
     depress
    -0.07
    _spaces
    -0.07
    nine
    -0.07
    ebel
    -0.07
     squeez
    -0.07
     cramps
    -0.07
    POSITIVE LOGITS
    .kafka
    0.13
    Kafka
    0.11
     kafka
    0.10
     Kafka
    0.10
     asynchronous
    0.10
    .notification
    0.10
     dispatched
    0.10
    .analytics
    0.10
     emitted
    0.10
     notification
    0.10
    Act Density 0.012%

    No Known Activations