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

    Neuronpedia

    INDEX
    Explanations

    l

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting bibliographic citation tokens, particularly journal-name abbreviations in reference lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ERSHEY
    -0.07
    _kel
    -0.07
    .vec
    -0.06
    ledi
    -0.06
    öğ
    -0.06
    uzey
    -0.06
     čt
    -0.06
     Roz
    -0.06
    .faceVertexUvs
    -0.06
     minutos
    -0.06
    POSITIVE LOGITS
     Illustrated
    0.06
    dr
    0.06
     umbrella
    0.06
     via
    0.06
     Revised
    0.06
     cuenta
    0.06
    >,↵
    0.06
     vign
    0.06
     Valley
    0.06
     setLocation
    0.06
    Act Density 0.001%

    No Known Activations