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

    Neuronpedia

    INDEX
    Explanations

    define

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defenses
    0.54
     +
    0.52
     verhindert
    0.52
     against
    0.51
     pfl
    0.50
     to
    0.50
     behandelt
    0.50
     privilegi
    0.50
    膑
    0.49
     verm
    0.49
    POSITIVE LOGITS
    定義
    0.94
    Defining
    0.92
    Define
    0.91
    Defined
    0.84
    defined
    0.83
     Defines
    0.83
     Defining
    0.81
     define
    0.80
     정의
    0.79
     defines
    0.77
    Act Density 0.023%

    No Known Activations