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

    Neuronpedia

    INDEX
    Explanations

    defining specific objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retras
    0.53
     headphones
    0.50
     Australien
    0.49
     automóvil
    0.48
     Gesch
    0.47
     automóviles
    0.46
     nvidia
    0.46
    凄い
    0.46
     Chromecast
    0.46
     ተመሳሳይ
    0.45
    POSITIVE LOGITS
     define
    0.70
    Defining
    0.65
    define
    0.64
     defined
    0.64
     Define
    0.63
    Define
    0.63
     Objectives
    0.60
     defines
    0.59
     정의
    0.57
    defined
    0.57
    Act Density 0.259%

    No Known Activations