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

    Neuronpedia

    INDEX
    Explanations

    friend

    np_max-act · gemini-2.0-flash

    The neuron activates most strongly on proper names or titles (especially movie titles) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ;;
    -0.08
     shit
    -0.07
     installer
    -0.06
     sued
    -0.06
    名
    -0.06
     mối
    -0.06
     Nose
    -0.06
     tắc
    -0.06
     suing
    -0.06
     bean
    -0.06
    POSITIVE LOGITS
     Schl
    0.07
    Consulta
    0.07
    zeich
    0.06
     hashlib
    0.06
    immutable
    0.06
     destined
    0.06
    .articles
    0.06
     Giuliani
    0.06
     ομά
    0.06
    ски
    0.06
    Act Density 0.061%

    No Known Activations