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

    Neuronpedia

    INDEX
    Explanations

    sentences where the author is explaining or making conclusions

    oai_token-act-pair · gemini-2.0-flash

    seeming, appearing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    المشاركات
    -0.78
    جغرافيا
    -0.67
    [@"
    -0.67
    BeginContext
    -0.63
    IBOutlet
    -0.61
    rawDesc
    -0.56
     revanche
    -0.56
     resourceCulture
    -0.56
    सन्दर्भ
    -0.54
    ExecuteReader
    -0.53
    POSITIVE LOGITS
     seems
    1.95
     Seems
    1.91
    seems
    1.85
     seem
    1.84
     apparently
    1.84
     Apparently
    1.83
    Seems
    1.82
    apparently
    1.78
    Apparently
    1.71
     appears
    1.64
    Act Density 1.379%

    No Known Activations