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

    Neuronpedia

    INDEX
    Explanations

    names in credits

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are parts of character names listed in a film’s cast list.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     React
    -0.07
    ct
    -0.07
    _lvl
    -0.07
     політики
    -0.07
     productId
    -0.06
     Via
    -0.06
     мінім
    -0.06
     služby
    -0.06
    _lib
    -0.06
    "log
    -0.06
    POSITIVE LOGITS
    _TEMPLATE
    0.06
     flyer
    0.06
    emaakt
    0.06
     legally
    0.06
    _large
    0.06
     fark
    0.06
     Looks
    0.06
    Hier
    0.06
    .about
    0.06
     able
    0.06
    Act Density 0.011%

    No Known Activations