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

    Neuronpedia

    INDEX
    Explanations

    future tense and first-person-plural

    np_max-act · gemini-2.0-flash

    This neuron consistently fires on first-person plural pronouns (especially “We”) used to introduce one’s own work or key points in academic prose.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Pt
    -0.06
    opencv
    -0.06
    ادر
    -0.06
    regor
    -0.06
    VertexBuffer
    -0.06
    很多
    -0.06
    fad
    -0.06
    thumbnails
    -0.05
    False
    -0.05
    dden
    -0.05
    POSITIVE LOGITS
    чого
    0.07
     التش
    0.07
     новых
    0.07
     حل
    0.07
     pohy
    0.07
     poměr
    0.07
     we
    0.07
     основных
    0.06
     نتیجه
    0.06
     '}';↵
    0.06
    Act Density 0.014%

    No Known Activations