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

    Neuronpedia

    INDEX
    Explanations

    boolean true false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Havre
    0.76
     விவர
    0.73
    rawl
    0.73
     কেন্দ
    0.69
    athons
    0.68
     उत्पा
    0.68
     алу
    0.66
     バッグ
    0.66
    CTED
    0.64
    לך
    0.64
    POSITIVE LOGITS
     boolean
    3.24
     Boolean
    3.21
    Boolean
    3.20
    boolean
    3.05
     bool
    3.02
    bool
    2.94
    Bool
    2.90
     Bool
    2.67
     BOOLE
    2.66
    BOOLE
    2.49
    Act Density 1.239%

    No Known Activations