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

    Neuronpedia

    INDEX
    Explanations

    code/language transformation

    np_max-act · gemini-2.0-flash

    This neuron does not reliably activate on any tokens—it appears effectively inactive (a “dead” neuron) that does not detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    everyone
    -0.07
    大学
    -0.07
    _prec
    -0.06
    jak
    -0.06
     affiliate
    -0.06
     Consultant
    -0.06
     camar
    -0.06
    _properties
    -0.06
     /\.(
    -0.06
    ,unsigned
    -0.06
    POSITIVE LOGITS
     американ
    0.07
     Gib
    0.07
    CH
    0.07
    річ
    0.06
     Rutgers
    0.06
    мерикан
    0.06
     Chili
    0.06
     skate
    0.06
    .setBorder
    0.06
    .cl
    0.06
    Act Density 0.014%

    No Known Activations