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

    Neuronpedia

    INDEX
    Explanations

    actions around inflation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     authorship
    0.77
     extro
    0.76
    ucidation
    0.73
     Fauna
    0.71
    ક્ટ
    0.70
     Sabbath
    0.68
     تاس
    0.67
    βο
    0.67
    ಿದ್ದೇನೆ
    0.67
    ష్టం
    0.67
    POSITIVE LOGITS
     inflation
    3.30
    Inflation
    2.99
     inflationary
    2.94
    inflation
    2.93
     Inflation
    2.92
     inflación
    2.75
     infl
    2.44
     Infl
    2.37
    Infl
    2.32
     inflating
    2.24
    Act Density 0.148%

    No Known Activations