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

    Neuronpedia

    INDEX
    Explanations

    User input requests

    np_max-act · gemini-2.0-flash

    The neuron fires on explicit mentions or requests to include “emoji”/“emojis” in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cil
    -0.06
     milion
    -0.06
     STATES
    -0.06
     genocide
    -0.06
    -Version
    -0.06
    δό
    -0.06
    (equal
    -0.06
    776
    -0.06
     UP
    -0.06
    ีนาคม
    -0.06
    POSITIVE LOGITS
     Cork
    0.07
     gebru
    0.07
     known
    0.07
    //
↵
↵
    0.06
    ypsy
    0.06
    608
    0.06
    _BEGIN
    0.06
     textbook
    0.06
    _cycle
    0.06
    .bean
    0.06
    Act Density 0.026%

    No Known Activations