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

    Neuronpedia

    INDEX
    Explanations

    Discover, Join, Learn

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generally
    0.55
     অবশ্য
    0.54
     albeit
    0.54
     priori
    0.53
    generally
    0.51
    ждению
    0.50
     insofar
    0.50
     somewhat
    0.49
     initialization
    0.49
     leeway
    0.49
    POSITIVE LOGITS
    Discover
    1.31
     Discover
    1.27
    Join
    1.20
     Découvrez
    1.16
     discover
    1.14
     Join
    1.13
    Whether
    1.10
     Whether
    1.09
    Learn
    1.08
    Enjoy
    1.08
    Act Density 0.200%

    No Known Activations