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

    Neuronpedia

    INDEX
    Explanations

    multiple choice options

    np_max-act · gemini-2.0-flash

    The neuron fires on the appearance of the answer choice “C” token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,get
    -0.07
    сю
    -0.07
    ，就是
    -0.07
     migrate
    -0.06
     described
    -0.06
    sse
    -0.06
    __(/*!
    -0.06
    IED
    -0.06
     pued
    -0.06
     eighth
    -0.06
    POSITIVE LOGITS
     Venom
    0.07
    ouses
    0.06
     gauss
    0.06
    uang
    0.06
     nodeList
    0.06
    ектив
    0.06
    ฤด
    0.06
    commons
    0.06
    aleza
    0.06
    target
    0.06
    Act Density 0.002%

    No Known Activations