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

    Neuronpedia

    INDEX
    Explanations

    certainty/doubt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doubt
    -1.66
     doubtful
    -1.63
    doubt
    -1.46
    Doubt
    -1.45
     Doubt
    -1.41
     doubts
    -1.38
     doute
    -1.37
     uncertainty
    -1.33
     uncertain
    -1.28
     certainty
    -1.20
    POSITIVE LOGITS
     AssemblyCulture
    0.58
    ness
    0.51
    ries
    0.51
    ibatis
    0.51
    ništ
    0.51
     AdapterView
    0.51
     يول
    0.51
    MigrationBuilder
    0.51
    yship
    0.50
    Sklici
    0.49
    Act Density 0.106%

    No Known Activations