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

    Neuronpedia

    INDEX
    Explanations

    label

    np_max-act · gemini-2.0-flash

    The neuron fires on LaTeX equation‐label markers (e.g. “\label{…}”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    尿
    -0.06
    _merged
    -0.06
     Accept
    -0.06
    اسات
    -0.06
     Rank
    -0.06
     problémy
    -0.06
     meetings
    -0.06
     Sets
    -0.06
    vědom
    -0.06
    IColor
    -0.06
    POSITIVE LOGITS
     absolutely
    0.07
     objections
    0.06
    (Packet
    0.06
     salvar
    0.06
     Deploy
    0.06
     monument
    0.06
    plate
    0.06
    landı
    0.06
    icontains
    0.06
     lanç
    0.06
    Act Density 0.001%

    No Known Activations