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

    Neuronpedia

    INDEX
    Explanations

    slave

    np_max-act · gemini-2.0-flash

    This neuron fires whenever the word “slave” appears in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     yazar
    -0.08
    imuth
    -0.08
     collided
    -0.08
    eldig
    -0.07
    .point
    -0.07
     emitted
    -0.07
     Mood
    -0.07
    .console
    -0.07
    Booking
    -0.07
     Morrison
    -0.06
    POSITIVE LOGITS
     slave
    0.13
     slaves
    0.13
     Slave
    0.12
    Slave
    0.09
    slave
    0.08
     slavery
    0.08
    奴
    0.08
    py
    0.07
     раб
    0.07
     enslaved
    0.07
    Act Density 0.006%

    No Known Activations