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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash

    This neuron detects instructions asking which items appear in both of two provided lists (i.e., asking for their intersection).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    educt
    -0.06
     Hue
    -0.06
    خان
    -0.06
     slee
    -0.06
     pois
    -0.06
    -circle
    -0.06
     silicone
    -0.06
    -empty
    -0.06
     isolate
    -0.06
     uncomfort
    -0.06
    POSITIVE LOGITS
    Absolutely
    0.06
    _login
    0.06
     routinely
    0.06
    xic
    0.06
     Absolutely
    0.06
    ยอด
    0.06
    formedURLException
    0.06
    BALL
    0.06
    ifying
    0.05
    少女
    0.05
    Act Density 0.001%

    No Known Activations