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

    Neuronpedia

    INDEX
    Explanations

    double standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     siku
    0.48
     orthogonal
    0.45
     trek
    0.45
     conex
    0.45
     net
    0.44
     berg
    0.43
     sis
    0.43
     compensated
    0.42
     potted
    0.42
     patho
    0.42
    POSITIVE LOGITS
    standards
    0.97
     standards
    0.90
    Standards
    0.87
    double
    0.84
     double
    0.83
    Double
    0.81
     Standards
    0.81
     стандарта
    0.74
     станда
    0.72
    ダブル
    0.71
    Act Density 0.004%

    No Known Activations