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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive emotion and gratitude

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.57
    (!__
    -0.56
    請繼續往下閱讀
    -0.52
     οποίο
    -0.52
     betweenstory
    -0.52
    الحياه
    -0.51
    kező
    -0.51
     scoper
    -0.50
    ulás
    -0.49
    üyada
    -0.47
    POSITIVE LOGITS
     Thank
    0.68
     thank
    0.67
    Thank
    0.65
    thank
    0.63
    queryInterface
    0.58
    mergeFrom
    0.56
     FetchType
    0.56
     vPvB
    0.56
    flashdata
    0.55
    AppMethodBeat
    0.54
    Act Density 2.183%

    No Known Activations